Add development AXQ pack AX-Devstral-Small-2505-MLX-AXQ-4bit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,38 @@
+---
+license: apache-2.0
+library_name: mlx
+tags:
+- mlx
+- axquant
+- axq
+- development
+pipeline_tag: text-generation
+---
+
+# AX-Devstral-Small-2505-MLX-AXQ-4bit
+
+**Development** AXQuant (AXQ) MLX pack from BF16 via `axquant quantize` (architecture-prior ladder). **Not** a certified release.
+
+| Field | Value |
+| --- | --- |
+| Source | `mistralai/Devstral-Small-2505` |
+| Measured total BPW | `4.949963393465118` |
+| MTP present | `False` |
+| Runtime smoke (mlx-lm) | `True` |
+| AX Engine model-manifest | `True` |
+| Evidence | `architecture_prior` |
+
+## Load (MLX-LM)
+
+```python
+from mlx_lm import load, generate
+model, tokenizer = load("AutomatosX/AX-Devstral-Small-2505-MLX-AXQ-4bit")
+print(generate(model, tokenizer, prompt="Hello", max_tokens=64))
+```
+
+## Notes
+
+- Product naming: `AX-<Base>-MLX-AXQ-<4bit|6bit>[-MTP]`
+- Protection floors may raise realized BPW above the requested target (especially small / heavily protected models).
+- Nemotron thin support may not generate `model-manifest.json` for AX Engine yet; MLX-LM path still applies.
+- Formal certification requires measured analyze → plan → validate → release-audit.

axquant_manifest.json

@@ -0,0 +1,191 @@
+{
+  "axquant_version": "1.0.0",
+  "calibration": null,
+  "created_at": "2026-08-02T18:31:02.216726Z",
+  "effective_bpw": 4.949927508451917,
+  "files": [
+    {
+      "path": "README.md",
+      "sha256": "748c964f9b7e5f2c3770ce013bbc0153be7c54311d9692c343b6188eefe77ac6",
+      "size_bytes": 81
+    },
+    {
+      "path": "axquant_plan.json",
+      "sha256": "334936cd7de68d6a306aaea96a371268f7b6f82fbc26ebfb16d9ba511de824b7",
+      "size_bytes": 337382
+    },
+    {
+      "path": "axquant_quantizer_execution.json",
+      "sha256": "c5d5499fd4fd3d5ac05b75ae81c539b679a749af0b6bbe5fd1dd695fb2fb7269",
+      "size_bytes": 68529
+    },
+    {
+      "path": "axquant_runtime.json",
+      "sha256": "a0163c63a8fab3e93ef6c027e4a509fcd380267b4252b4137cb8213c9695917b",
+      "size_bytes": 1643
+    },
+    {
+      "path": "chat_template.jinja",
+      "sha256": "abf41beccbd34014b52ada4fdefaa0572201d40f85ff8114f1fa5dde0949c89a",
+      "size_bytes": 1590
+    },
+    {
+      "path": "config.json",
+      "sha256": "ad3c166ac4958c8542e114ea1f0aba2546253f5c3d90d678e21de09dba4c0057",
+      "size_bytes": 77944
+    },
+    {
+      "path": "generation_config.json",
+      "sha256": "46a6e46680317fe06de9a5e1b2bcc4cf2965245b4994dab4600ba4be4860f1b8",
+      "size_bytes": 111
+    },
+    {
+      "path": "model-00001-of-00003.safetensors",
+      "sha256": "d0a2e91e9d8ca5322df7d3d184ada4f68f9c5a4772d551d1fc9d8e5a1135c81b",
+      "size_bytes": 5308086419
+    },
+    {
+      "path": "model-00002-of-00003.safetensors",
+      "sha256": "464f89aa6a7b57c8f826c75a9c3fea284e39eb6dbc114abba21a0d3a88083642",
+      "size_bytes": 5314707223
+    },
+    {
+      "path": "model-00003-of-00003.safetensors",
+      "sha256": "9060d2f447d0203a0459a36cba4ef510e3c4eebb4cae92c8228129bc123407e5",
+      "size_bytes": 3962522975
+    },
+    {
+      "path": "model.safetensors.index.json",
+      "sha256": "49f2e5cc33c02b3040dbff542839e016af6fe9b0ba8aaeea67e31df919ac715a",
+      "size_bytes": 79244
+    },
+    {
+      "path": "tokenizer.json",
+      "sha256": "b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949",
+      "size_bytes": 17078037
+    },
+    {
+      "path": "tokenizer_config.json",
+      "sha256": "56838aafa405e68956ce4e39f3f5443a48d9587302cb044d85355eac111ab201",
+      "size_bytes": 345
+    }
+  ],
+  "format": "mlx",
+  "logical_parameters": 23572403200,
+  "main_logical_parameters": 23572403200,
+  "main_weight_file_size_bytes": 14585316617,
+  "measured_main_bpw": 4.949963393465118,
+  "measured_total_bpw": 4.949963393465118,
+  "mtp_acceptance_retention": null,
+  "mtp_distribution": {},
+  "mtp_measured_speedup": null,
+  "mtp_policy": {
+    "candidate_bits": [
+      8,
+      16
+    ],
+    "min_bits": 8,
+    "mode": "protected",
+    "optimize_for_acceptance": true,
+    "preserve_external_sidecar": true,
+    "protect_norms": true,
+    "protect_output_head": true
+  },
+  "mtp_present": false,
+  "mtp_weight_file_size_bytes": 0,
+  "plan_sha256": "0dd9d89a5c094d985bbdfc0ab51aa556ccf593e1e0f58fdb5a242cabc5c438a1",
+  "profile": "general",
+  "protected_weight_file_size_bytes": 0,
+  "quantizer": "axquant",
+  "runtime": {
+    "ax_engine": {
+      "decode_kernel": null,
+      "fused_mtp": null,
+      "kernel_evidence": "unmeasured",
+      "model_manifest": "model-manifest.json",
+      "preferred_group_size": 32
+    },
+    "compatible_runtimes": [
+      {
+        "compatibility_level": "B",
+        "manifest": "config.json",
+        "mtp_support": "runtime-dependent",
+        "name": "mlx-lm",
+        "notes": [
+          "Standard backbone inference is the compatibility target.",
+          "AXQuant MTP metadata may be ignored by MLX-LM."
+        ],
+        "standard_inference": true,
+        "standard_mlx_weights": true,
+        "support_level": "standard-inference"
+      }
+    ],
+    "created_at": "2026-08-02T18:30:54.875389Z",
+    "kv_cache": null,
+    "memory_policy": {
+      "kv_cache_precision": "runtime-default",
+      "mtp_buffers": "not-required",
+      "prefix_cache": "runtime-managed",
+      "unified_memory_safety_margin": "benchmark-required"
+    },
+    "mtp": {
+      "acceptance_retention": null,
+      "detected": false,
+      "draft_tokens": null,
+      "enabled_by_default": false,
+      "head_precision": null,
+      "measured_speedup": null,
+      "optimized": false,
+      "recommended_temperature_max": null,
+      "sidecar_file": null,
+      "verification_mode": null
+    },
+    "optimization_scope": "text-path",
+    "primary_runtime": {
+      "compatibility_level": "A",
+      "manifest": "model-manifest.json",
+      "mtp_support": "native",
+      "name": "ax-engine",
+      "notes": [
+        "Runtime claims require a passing AX Engine doctor and benchmark report."
+      ],
+      "standard_inference": true,
+      "standard_mlx_weights": true,
+      "support_level": "optimized"
+    },
+    "schema_version": "axquant.runtime.v1"
+  },
+  "schema_version": "axquant.artifact.v2",
+  "software_versions": {
+    "ax_engine": null,
+    "axquant": "1.0.0",
+    "mlx": "0.32.0",
+    "mlx_lm": "0.31.3",
+    "pydantic": "2.13.4",
+    "python": "3.13.14",
+    "safetensors": "0.8.0"
+  },
+  "source_model": {
+    "architecture": "MistralForCausalLM",
+    "format": "mlx",
+    "local_path": "/Volumes/Ext4T-02/axquant/models/Devstral-Small-2505-bf16",
+    "model_id": "mistralai/Devstral-Small-2505",
+    "revision": null
+  },
+  "target_class": "4bit",
+  "weight_distribution": {
+    "4bit": {
+      "fraction": 0.9430439065288005,
+      "parameters": 22229811200
+    },
+    "8bit": {
+      "fraction": 0.028469250008416623,
+      "parameters": 671088640
+    },
+    "bf16": {
+      "fraction": 0.028486843462782786,
+      "parameters": 671503360
+    }
+  },
+  "weight_file_size_bytes": 14585316617
+}

axquant_quantizer_execution.json

@@ -0,0 +1,2817 @@
+{
+  "created_at": "2026-08-02T18:30:54.870992Z",
+  "plan_sha256": "0dd9d89a5c094d985bbdfc0ab51aa556ccf593e1e0f58fdb5a242cabc5c438a1",
+  "records": [
+    {
+      "bits": 8,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.embed_tokens",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.0.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.0.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.0.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.0.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.0.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.0.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.0.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.1.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.1.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.1.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.1.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.1.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.1.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.1.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.2.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.2.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.2.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.2.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.2.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.2.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.2.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.3.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.3.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.3.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.3.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.3.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.3.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.3.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.4.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.4.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.4.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.4.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.4.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.4.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.4.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.5.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.5.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.5.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.5.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.5.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.5.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.5.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.6.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.6.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.6.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.6.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.6.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.6.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.6.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.7.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.7.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.7.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.7.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.7.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.10.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.10.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.10.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.10.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.10.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.10.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.10.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.11.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.11.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.11.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.11.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.11.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.11.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.7.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.7.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.8.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.8.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.8.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.8.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.8.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.8.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.8.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.9.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.9.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.9.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.9.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.9.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.9.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.9.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.11.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.12.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.12.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.12.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.12.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.12.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.12.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.12.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.13.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.13.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.13.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.13.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.13.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.13.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.13.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.14.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.14.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.14.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.14.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.14.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.14.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.14.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.15.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.15.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.15.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.15.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.15.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.15.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.15.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.16.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.16.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.16.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.16.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.16.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.16.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.16.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.17.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.17.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.17.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.17.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.17.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.17.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.17.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.18.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.18.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.18.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.18.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.18.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.18.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.18.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.19.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.19.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.19.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.19.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.19.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.19.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.19.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.20.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.20.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.20.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.20.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.20.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.20.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.20.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.21.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.21.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.21.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.21.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.21.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.21.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.21.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.22.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.22.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.22.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.22.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.22.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.22.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.22.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.23.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.23.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.23.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.23.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.23.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.23.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.23.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.24.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.24.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.24.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.24.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.24.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.24.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.24.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.25.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.25.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.25.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.25.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.25.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.25.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.25.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.26.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.26.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.26.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.26.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.26.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.26.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.26.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.27.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.27.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.27.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.27.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.27.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.27.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.27.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.28.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.28.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.28.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.28.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.28.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.28.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.28.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.29.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.29.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.29.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.29.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.29.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.29.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.29.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.30.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.30.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.30.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.30.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.30.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.30.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.30.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.31.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.31.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.31.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.31.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.31.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.31.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.31.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.32.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.32.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.32.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.32.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.32.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.32.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.32.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.33.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.33.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.33.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.33.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.33.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.33.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.33.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.34.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.34.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.34.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.34.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.34.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.34.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.34.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.35.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.35.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.35.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.35.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.35.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.35.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.35.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.36.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.36.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.36.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.36.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.36.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.36.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.36.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.37.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.37.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.37.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.37.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.37.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.37.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.37.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.38.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.38.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.38.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.38.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.38.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.38.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.38.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.39.mlp.down_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.39.mlp.gate_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 64,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.39.mlp.up_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.39.self_attn.k_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.39.self_attn.o_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.39.self_attn.q_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    },
+    {
+      "bits": 4,
+      "fallback": false,
+      "group_size": 32,
+      "metadata": {},
+      "method": "affine",
+      "module_path": "model.layers.39.self_attn.v_proj",
+      "note": "MLX-LM affine packing",
+      "success": true
+    }
+  ],
+  "schema_version": "axquant.quantizer-execution.v1"
+}

axquant_runtime.json

@@ -0,0 +1,58 @@
+{
+  "ax_engine": {
+    "decode_kernel": null,
+    "fused_mtp": null,
+    "kernel_evidence": "unmeasured",
+    "model_manifest": "model-manifest.json",
+    "preferred_group_size": 32
+  },
+  "compatible_runtimes": [
+    {
+      "compatibility_level": "B",
+      "manifest": "config.json",
+      "mtp_support": "runtime-dependent",
+      "name": "mlx-lm",
+      "notes": [
+        "Standard backbone inference is the compatibility target.",
+        "AXQuant MTP metadata may be ignored by MLX-LM."
+      ],
+      "standard_inference": true,
+      "standard_mlx_weights": true,
+      "support_level": "standard-inference"
+    }
+  ],
+  "created_at": "2026-08-02T18:30:54.875389Z",
+  "kv_cache": null,
+  "memory_policy": {
+    "kv_cache_precision": "runtime-default",
+    "mtp_buffers": "not-required",
+    "prefix_cache": "runtime-managed",
+    "unified_memory_safety_margin": "benchmark-required"
+  },
+  "mtp": {
+    "acceptance_retention": null,
+    "detected": false,
+    "draft_tokens": null,
+    "enabled_by_default": false,
+    "head_precision": null,
+    "measured_speedup": null,
+    "optimized": false,
+    "recommended_temperature_max": null,
+    "sidecar_file": null,
+    "verification_mode": null
+  },
+  "optimization_scope": "text-path",
+  "primary_runtime": {
+    "compatibility_level": "A",
+    "manifest": "model-manifest.json",
+    "mtp_support": "native",
+    "name": "ax-engine",
+    "notes": [
+      "Runtime claims require a passing AX Engine doctor and benchmark report."
+    ],
+    "standard_inference": true,
+    "standard_mlx_weights": true,
+    "support_level": "optimized"
+  },
+  "schema_version": "axquant.runtime.v1"
+}

chat_template.jinja

@@ -0,0 +1,25 @@
+{%- set today = strftime_now("%Y-%m-%d") %}
+{%- set default_system_message = "You are Devstral, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\nYour knowledge base was last updated on 2023-10-01. The current date is " + today + ".\n\nWhen you're not sure about some information, you say that you don't have the information and don't make up anything.\nIf the user's question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. \"What are some good restaurants around me?\" => \"Where are you?\" or \"When is the next flight to Tokyo\" => \"Where do you travel from?\")" %}
+
+{{- bos_token }}
+
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content'] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = default_system_message %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}
+
+{%- for message in loop_messages %}
+    {%- if message['role'] == 'user' %}
+        {{- '[INST]' + message['content'] + '[/INST]' }}
+    {%- elif message['role'] == 'system' %}
+        {{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}
+    {%- elif message['role'] == 'assistant' %}
+        {{- message['content'] + eos_token }}
+    {%- else %}
+        {{- raise_exception('Only user, system and assistant roles are supported!') }}
+    {%- endif %}
+{%- endfor %}

config.json

@@ -0,0 +1,2846 @@
+{
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 32768,
+    "max_position_embeddings": 131072,
+    "model_type": "mistral",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 8,
+    "quantization": {
+        "group_size": 32,
+        "bits": 4,
+        "mode": "affine",
+        "model.embed_tokens": {
+            "group_size": 64,
+            "bits": 8,
+            "mode": "affine"
+        },
+        "model.layers.0.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.0.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.0.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.0.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.0.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.0.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.0.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.1.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.1.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.1.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.1.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.1.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.1.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.1.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.2.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.2.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.2.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.2.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.2.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.2.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.2.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.3.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.3.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.3.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.3.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.3.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.3.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.3.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.4.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.4.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.4.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.4.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.4.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.4.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.4.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.5.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.5.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.5.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.5.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.5.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.5.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.5.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.6.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.6.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.6.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.6.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.6.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.6.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.6.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.7.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.7.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.7.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.7.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.7.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.7.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.7.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.8.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.8.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.8.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.8.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.8.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.8.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.8.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.9.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.9.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.9.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.9.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.9.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.9.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.9.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.10.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.10.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.10.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.10.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.10.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.10.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.10.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.11.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.11.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.11.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.11.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.11.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.11.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.11.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.12.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.12.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.12.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.12.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.12.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.12.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.12.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.13.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.13.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.13.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.13.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.13.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.13.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.13.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.14.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.14.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.14.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.14.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.14.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.14.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.14.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.15.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.15.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.15.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.15.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.15.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.15.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.15.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.16.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.16.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.16.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.16.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.16.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.16.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.16.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.17.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.17.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.17.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.17.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.17.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.17.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.17.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.18.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.18.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.18.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.18.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.18.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.18.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.18.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.19.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.19.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.19.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.19.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.19.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.19.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.19.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.20.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.20.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.20.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.20.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.20.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.20.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.20.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.21.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.21.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.21.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.21.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.21.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.21.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.21.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.22.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.22.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.22.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.22.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.22.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.22.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.22.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.23.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.23.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.23.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.23.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.23.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.23.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.23.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.24.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.24.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.24.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.24.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.24.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.24.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.24.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.25.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.25.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.25.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.25.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.25.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.25.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.25.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.26.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.26.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.26.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.26.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.26.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.26.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.26.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.27.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.27.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.27.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.27.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.27.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.27.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.27.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.28.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.28.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.28.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.28.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.28.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.28.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.28.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.29.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.29.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.29.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.29.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.29.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.29.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.29.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.30.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.30.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.30.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.30.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.30.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.30.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.30.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.31.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.31.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.31.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.31.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.31.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.31.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.31.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.32.self_attn.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.32.self_attn.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.32.self_attn.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.32.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.32.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.32.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.32.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.33.self_attn.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.33.self_attn.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.33.self_attn.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.33.self_attn.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.33.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.33.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.33.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.34.self_attn.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.34.self_attn.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.34.self_attn.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.34.self_attn.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.34.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.34.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.34.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.35.self_attn.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.35.self_attn.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.35.self_attn.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.35.self_attn.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.35.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.35.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.35.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.36.self_attn.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.36.self_attn.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.36.self_attn.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.36.self_attn.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.36.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.36.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.36.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.37.self_attn.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.37.self_attn.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.37.self_attn.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.37.self_attn.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.37.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.37.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.37.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.38.self_attn.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.38.self_attn.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.38.self_attn.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.38.self_attn.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.38.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.38.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.38.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.39.self_attn.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.39.self_attn.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.39.self_attn.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.39.self_attn.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.39.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.39.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.39.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        }
+    },
+    "quantization_config": {
+        "group_size": 32,
+        "bits": 4,
+        "mode": "affine",
+        "model.embed_tokens": {
+            "group_size": 64,
+            "bits": 8,
+            "mode": "affine"
+        },
+        "model.layers.0.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.0.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.0.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.0.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.0.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.0.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.0.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.1.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.1.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.1.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.1.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.1.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.1.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.1.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.2.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.2.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.2.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.2.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.2.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.2.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.2.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.3.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.3.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.3.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.3.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.3.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.3.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.3.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.4.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.4.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.4.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.4.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.4.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.4.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.4.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.5.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.5.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.5.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.5.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.5.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.5.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.5.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.6.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.6.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.6.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.6.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.6.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.6.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.6.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.7.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.7.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.7.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.7.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.7.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.7.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.7.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.8.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.8.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.8.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.8.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.8.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.8.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.8.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.9.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.9.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.9.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.9.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.9.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.9.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.9.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.10.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.10.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.10.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.10.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.10.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.10.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.10.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.11.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.11.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.11.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.11.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.11.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.11.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.11.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.12.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.12.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.12.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.12.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.12.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.12.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.12.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.13.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.13.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.13.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.13.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.13.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.13.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.13.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.14.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.14.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.14.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.14.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.14.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.14.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.14.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.15.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.15.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.15.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.15.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.15.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.15.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.15.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.16.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.16.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.16.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.16.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.16.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.16.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.16.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.17.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.17.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.17.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.17.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.17.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.17.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.17.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.18.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.18.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.18.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.18.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.18.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.18.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.18.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.19.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.19.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.19.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.19.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.19.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.19.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.19.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.20.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.20.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.20.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.20.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.20.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.20.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.20.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.21.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.21.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.21.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.21.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.21.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.21.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.21.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.22.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.22.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.22.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.22.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.22.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.22.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.22.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.23.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.23.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.23.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.23.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.23.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.23.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.23.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.24.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.24.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.24.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.24.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.24.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.24.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.24.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.25.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.25.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.25.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.25.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.25.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.25.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.25.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.26.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.26.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.26.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.26.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.26.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.26.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.26.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.27.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.27.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.27.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.27.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.27.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.27.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.27.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.28.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.28.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.28.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.28.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.28.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.28.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.28.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.29.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.29.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.29.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.29.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.29.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.29.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.29.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.30.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.30.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.30.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.30.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.30.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.30.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.30.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.31.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.31.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.31.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.31.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.31.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.31.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.31.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.32.self_attn.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.32.self_attn.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.32.self_attn.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.32.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.32.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.32.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.32.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.33.self_attn.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.33.self_attn.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.33.self_attn.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.33.self_attn.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.33.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.33.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.33.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.34.self_attn.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.34.self_attn.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.34.self_attn.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.34.self_attn.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.34.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.34.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.34.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.35.self_attn.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.35.self_attn.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.35.self_attn.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.35.self_attn.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.35.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.35.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.35.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.36.self_attn.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.36.self_attn.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.36.self_attn.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.36.self_attn.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.36.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.36.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.36.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.37.self_attn.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.37.self_attn.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.37.self_attn.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.37.self_attn.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.37.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.37.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.37.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.38.self_attn.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.38.self_attn.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.38.self_attn.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.38.self_attn.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.38.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.38.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.38.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.39.self_attn.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.39.self_attn.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.39.self_attn.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.39.self_attn.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.39.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.39.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        },
+        "model.layers.39.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4,
+            "mode": "affine"
+        }
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.51.3",
+    "use_cache": true,
+    "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a2e91e9d8ca5322df7d3d184ada4f68f9c5a4772d551d1fc9d8e5a1135c81b
+size 5308086419

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:464f89aa6a7b57c8f826c75a9c3fea284e39eb6dbc114abba21a0d3a88083642
+size 5314707223

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9060d2f447d0203a0459a36cba4ef510e3c4eebb4cae92c8228129bc123407e5
+size 3962522975

model.safetensors.index.json

@@ -0,0 +1,933 @@
+{
+    "metadata": {
+        "total_size": 14585210880,
+        "total_parameters": 23572403200
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00003-of-00003.safetensors",
+        "model.embed_tokens.biases": "model-00001-of-00003.safetensors",
+        "model.embed_tokens.scales": "model-00001-of-00003.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.0.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.0.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.1.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.1.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.10.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.10.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.11.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.11.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.11.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.11.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.14.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.14.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.16.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.16.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.16.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.17.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.17.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.18.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.18.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.19.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.19.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.2.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.2.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.20.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.20.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.21.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.21.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.22.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.22.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.23.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.23.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.24.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.24.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.25.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.25.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.25.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.25.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.25.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.26.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.26.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.26.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.26.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.26.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.27.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.27.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.27.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.27.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.27.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.28.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.28.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.28.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.28.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.28.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.29.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.29.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.3.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.3.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.30.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.30.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.30.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.30.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.31.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.31.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.31.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.31.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.32.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.32.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.32.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.32.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.32.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.32.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.32.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.32.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.32.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.32.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.32.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.32.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.32.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.32.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.33.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.33.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.33.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.33.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.33.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.33.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.34.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.34.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.34.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.34.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.34.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.34.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.35.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.35.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.35.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.35.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.35.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.35.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.36.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.36.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.36.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.36.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.36.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.36.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.37.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.37.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.37.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.37.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.37.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.37.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.38.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.38.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.38.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.38.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.38.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.38.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.39.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.39.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.39.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.39.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.39.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.39.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.4.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.4.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.5.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.5.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.6.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.6.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.7.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.7.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.8.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.8.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.9.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.9.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.norm.weight": "model-00003-of-00003.safetensors"
+    }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
+size 17078037

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "is_local": true,
+  "legacy": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}