Upload folder using huggingface_hub

.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 +1,253 @@
+---
+language:
+- en
+library_name: transformers
+tags:
+- glm
+- glm4
+- MOE
+- pruning
+- compression
+- reap
+- cerebras
+- code
+- function-calling
+- agentic
+license: apache-2.0
+pipeline_tag: text-generation
+base_model:
+- zai/glm-4.7
+---
+
+<p align="center">
+  <em>𓌳 <strong>REAP</strong>𓌳  the Experts: Why Pruning Prevails for One-Shot MoE Compression</em><br>
+  <a href="https://arxiv.org/abs/2510.13999">📄 Paper</a> • <a href="https://github.com/CerebrasResearch/reap">💻 Code</a> • <a href="https://www.cerebras.ai/blog/reap">📝 Blog</a>
+</p>
+
+# GLM-4.7-REAP-30
+
+## ✨ Highlights
+
+**30% Expert-Pruned** GLM-4.7 optimized for **code generation**, **function calling**, and **agentic workflows**.
+
+Created using **[REAP (Router-weighted Expert Activation Pruning)](https://arxiv.org/abs/2510.13999)** by Cerebras:
+
+- **358B → 251B**: 30% of MoE experts pruned (112/160 remaining)
+- **Calibrated for Code & Tools**: Preserves coding and function-calling capabilities
+- **One-Shot Compression**: No fine-tuning required
+- **Drop-in Compatible**: Works with vLLM, Transformers, SGLang
+
+### 🙏 Acknowledgments
+
+- **[Prime Intellect](https://www.primeintellect.ai/)** — Compute sponsorship (8x H200 cluster)
+- **[Cerebras](https://www.cerebras.net/)** — [REAP methodology](https://arxiv.org/abs/2510.13999)
+
+---
+
+## 📋 Model Specifications
+
+| Property | Value |
+|----------|-------|
+| **Base Model** | [zai/glm-4.7](https://huggingface.co/zai/glm-4.7) |
+| **Architecture** | Sparse Mixture-of-Experts (SMoE) |
+| **Original Parameters** | 358B |
+| **Pruned Parameters** | 251B |
+| **Compression** | 30% experts removed |
+| **Experts per Layer** | 112 (was 160) |
+| **MoE Layers** | 92 |
+| **Activated Experts** | 8 per token |
+| **Precision** | BF16 |
+| **Disk Size** | ~470GB |
+| **VRAM Required** | ~470GB |
+
+---
+
+
+## 🔬 Calibration Dataset: Deep Dive
+
+REAP's effectiveness depends critically on **calibration data that represents the target use case**. We specifically optimized for **code generation**, **function/tool calling**, and **agentic workflows**.
+
+### Why These 3 Datasets?
+
+| Dataset | Samples | Purpose | Why It Matters |
+|---------|---------|---------|----------------|
+| [evol-codealpaca-v1](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1) | 700 | Code generation | **51% of mix** — Code tasks activate specific expert pathways; pruning without code calibration destroys coding ability |
+| [xlam-function-calling-60k](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k) | 330 | Function/tool calling | **24% of mix** — Tool use requires structured JSON output; experts handling schema generation must be preserved |
+| [SWE-smith-trajectories](https://huggingface.co/datasets/SWE-bench/SWE-smith-trajectories) | 330 | Agentic multi-turn | **24% of mix** — Real SWE-bench trajectories with tool calls, file edits, and multi-step reasoning |
+
+### The Science Behind Dataset Selection
+
+```
+REAP Algorithm:
+1. Forward pass calibration samples through model
+2. Record which experts activate and their magnitudes
+3. Compute saliency = router_weight × activation_norm
+4. Prune lowest-saliency experts
+
+Key Insight: Experts are TASK-SPECIFIC
+├── Some experts specialize in natural language
+├── Some experts specialize in code syntax
+├── Some experts specialize in JSON/structured output
+└── Some experts specialize in multi-turn context
+
+If calibration lacks code → code-specialized experts appear "unused" → get pruned → model loses coding ability
+```
+
+### Cerebras' Original Mix (from paper)
+
+Cerebras used the same 3 datasets in their GLM-4.6 REAP experiments:
+- evol-codealpaca-v1 for code generation
+- xlam-function-calling-60k for tool calling
+- SWE-smith-trajectories for agentic tasks
+
+We followed this exact recipe for reproducibility.
+
+### Combined Dataset
+
+Our calibration mix: [0xSero/glm47-reap-calibration-v2](https://huggingface.co/datasets/0xSero/glm47-reap-calibration-v2)
+
+
+---
+
+## 📦 Related Models
+
+| Model | Params | Experts | Size | Format |
+|-------|--------|---------|------|--------|
+| [GLM-4.7-REAP-30](https://huggingface.co/0xSero/GLM-4.7-REAP-30) | 251B | 112 | ~470GB | BF16 |
+| [GLM-4.7-REAP-35](https://huggingface.co/0xSero/GLM-4.7-REAP-35) | 233B | 104 | ~439GB | BF16 |
+| [GLM-4.7-REAP-40](https://huggingface.co/0xSero/GLM-4.7-REAP-40) | 218B | 96 | ~407GB | BF16 |
+| [GLM-4.7-REAP-45](https://huggingface.co/0xSero/GLM-4.7-REAP-45) | 197B | 88 | ~370GB | BF16 |
+| [GLM-4.7-REAP-50](https://huggingface.co/0xSero/GLM-4.7-REAP-50) | 179B | 80 | ~345GB | BF16 |
+| [GLM-4.7-REAP-40-W4A16](https://huggingface.co/0xSero/GLM-4.7-REAP-40-W4A16) | 218B | 96 | ~108GB | GPTQ |
+| [GLM-4.7-REAP-50-W4A16](https://huggingface.co/0xSero/GLM-4.7-REAP-50-W4A16) | 179B | 80 | ~92GB | GPTQ |
+
+---
+
+## 🚀 Deployment
+
+### vLLM (Recommended)
+
+```bash
+vllm serve 0xSero/GLM-4.7-REAP-30 \
+    --tensor-parallel-size 8 \
+    --trust-remote-code \
+    --dtype bfloat16
+```
+
+### Transformers
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained(
+    "0xSero/GLM-4.7-REAP-30",
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+    trust_remote_code=True
+)
+tokenizer = AutoTokenizer.from_pretrained("0xSero/GLM-4.7-REAP-30", trust_remote_code=True)
+
+messages = [{"role": "user", "content": "Write a Python function to merge two sorted lists."}]
+inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
+outputs = model.generate(inputs.to(model.device), max_new_tokens=512, temperature=0.7)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+---
+
+## 🧩 Reproduction
+
+### REAP Pruning Script
+
+
+```python
+#!/usr/bin/env python3
+"""
+REAP Pruning Script for MoE Models
+Adapted from: https://github.com/CerebrasResearch/reap
+"""
+
+import subprocess
+import sys
+
+def run_reap(
+    model_path: str,
+    compression_ratio: float,
+    dataset: str = "0xSero/glm47-reap-calibration-v2",
+    samples: int = 1360,
+    seed: int = 42,
+    distance: str = "angular",
+    reuse_observations: str = None,
+):
+    """
+    Run REAP expert pruning.
+
+    Args:
+        model_path: Path to base model
+        compression_ratio: 0.30 = prune 30%, keep 70%
+        dataset: Calibration dataset (code + tools + agentic)
+        samples: Number of calibration samples
+        seed: Random seed for reproducibility
+        distance: Distance metric for expert clustering
+        reuse_observations: Path to pre-computed observations for instant pruning
+    """
+    cmd = [
+        sys.executable, "src/reap/prune.py",
+        "--model-name", model_path,
+        "--dataset-name", dataset,
+        "--compression-ratio", str(compression_ratio),
+        "--prune-method", "reap",
+        "--seed", str(seed),
+        "--samples_per_category", str(samples),
+        "--model_max_length", "2048",
+        "--distance_measure", distance,
+        "--record_pruning_metrics_only", "true",
+    ]
+
+    if reuse_observations:
+        # Instant pruning: skip calibration, reuse precomputed expert scores
+        cmd.extend(["--load_observations", reuse_observations])
+
+    subprocess.run(cmd, check=True)
+
+# Example: Create 40% pruned model
+run_reap(
+    model_path="/path/to/GLM-4.7",
+    compression_ratio=0.40,  # Prune 40% of experts
+)
+```
+
+
+### Observation Reuse (Instant Multi-Ratio Pruning)
+
+REAP computes expert saliency scores during calibration. These scores are **compression-ratio independent**, enabling instant pruning at any ratio:
+
+```bash
+# First run: compute observations (~5 hours)
+python prune.py --compression-ratio 0.40 --output_file_name observations.pt
+
+# Subsequent runs: instant pruning (<5 minutes)
+python prune.py --compression-ratio 0.30 --load_observations observations.pt
+python prune.py --compression-ratio 0.50 --load_observations observations.pt
+```
+
+---
+
+## ⚖️ License
+
+Apache 2.0 (inherited from GLM-4)
+
+---
+
+## 🧾 Citation
+
+```bibtex
+@article{lasby2025reap,
+  title={REAP the Experts: Why Pruning Prevails for One-Shot MoE Compression},
+  author={Lasby, Mike and Lazarevich, Ivan and Sinnadurai, Nish and Lie, Sean and Ioannou, Yani and Thangarasa, Vithursan},
+  journal={arXiv preprint arXiv:2510.13999},
+  year={2025},
+  url={https://arxiv.org/abs/2510.13999}
+}
+```

chat_template.jinja

@@ -0,0 +1,86 @@
+[gMASK]<sop>
+{%- if tools -%}
+<|system|>
+# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{% for tool in tools %}
+{{ tool | tojson(ensure_ascii=False) }}
+{% endfor %}
+</tools>
+
+For each function call, output the function name and arguments within the following XML format:
+<tool_call>{function-name}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value><arg_key>{arg-key-2}</arg_key><arg_value>{arg-value-2}</arg_value>...</tool_call>{%- endif -%}
+{%- macro visible_text(content) -%}
+    {%- if content is string -%}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping -%}
+        {%- for item in content -%}
+            {%- if item is mapping and item.type == 'text' -%}
+                {{- item.text }}
+            {%- elif item is string -%}
+                {{- item }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+{%- set ns = namespace(last_user_index=-1) %}
+{%- for m in messages %}
+    {%- if m.role == 'user' %}
+        {% set ns.last_user_index = loop.index0 -%}
+    {%- endif %}
+{%- endfor %}
+{% for m in messages %}
+{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}
+{%- elif m.role == 'assistant' -%}
+<|assistant|>
+{%- set reasoning_content = '' %}
+{%- set content = visible_text(m.content) %}
+{%- if m.reasoning_content is string %}
+    {%- set reasoning_content = m.reasoning_content %}
+{%- else %}
+    {%- if '</think>' in content %}
+        {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+        {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+    {%- endif %}
+{%- endif %}
+{%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content -%}
+{{ '<think>' + reasoning_content.strip() +  '</think>'}}
+{%- else -%}
+{{ '</think>' }}
+{%- endif -%}
+{%- if content.strip() -%}
+{{ content.strip() }}
+{%- endif -%}
+{% if m.tool_calls %}
+{% for tc in m.tool_calls %}
+{%- if tc.function %}
+    {%- set tc = tc.function %}
+{%- endif %}
+{{- '<tool_call>' + tc.name -}}
+{% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %}
+{% endif %}
+{%- elif m.role == 'tool' -%}
+{%- if m.content is string -%}
+{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+    {{- '<|observation|>' }}
+{%- endif %}
+{{- '<tool_response>' }}
+{{- m.content }}
+{{- '</tool_response>' }}
+{%- else -%}
+<|observation|>{% for tr in m.content %}
+<tool_response>{{ tr.output if tr.output is defined else tr }}</tool_response>{% endfor -%}
+{% endif -%}
+{%- elif m.role == 'system' -%}
+<|system|>{{ visible_text(m.content) }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    <|assistant|>{{- '</think>' if (enable_thinking is defined and not enable_thinking) else '<think>' -}}
+{%- endif -%}

config.json

@@ -0,0 +1,43 @@
+{
+  "architectures": [
+    "Glm4MoeForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "first_k_dense_replace": 3,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 202752,
+  "model_type": "glm4_moe",
+  "moe_intermediate_size": 1536,
+  "n_group": 1,
+  "n_routed_experts": 112,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 96,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 92,
+  "num_key_value_heads": 8,
+  "num_nextn_predict_layers": 1,
+  "pad_token_id": 151329,
+  "partial_rotary_factor": 0.5,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "routed_scaling_factor": 2.5,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "use_qk_norm": true,
+  "vocab_size": 151552
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "pad_token_id": 151329,
+  "transformers_version": "4.57.3"
+}

model-00001-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a43d3af802b963551e4cc900aa5de17bee95beb16e8f6834e8306cf2305020e0
+size 4986172648

model-00002-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b0c53afa704399e0b37e66f21b008898c5dbaa956c663105e59f0e233ce80c3
+size 4992457518

model-00003-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d0be7d1ed38ffc53a242ceb40c6cbdf85f725923d34718934dcc3a2f2a84670
+size 4882356341

model-00004-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a3f995df536e59a650dc0a9c3b31776fd82457a6da853484252d3d8f084c36
+size 4986018121

model-00005-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:898b72aee53773a1a154ad417968e15ba87138caa815199283fdf2fe1afef591
+size 4992457505

model-00006-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc3a3b2fd43b54f1e1124e779448616e8873741cf4b37b0efd2290c23e7d2596
+size 4992457518

model-00007-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c70c84d714654ca11ffdabc90c14ee4fb6b9a6da75bcd2c60d81de66b38fc12b
+size 4992457518

model-00008-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c993c74e5e24fe092e20e63d2f8868c6f7da21069d9b64dad09ca0163e15f0be
+size 4992457518

model-00009-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:550a4f87dd09dacc1fa5684dfba29a3fe53419467a776cabce60ea4048bd024c
+size 4992457651

model-00010-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94dd67c4819699e14818591ba7282ea3767b1159a7b01f360ee196f423db1b4d
+size 4992457831

model-00011-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30216766736313fbf7e0dc4c63fce3e86708d746e82f7b62897a70656465cbfd
+size 4992457831

model-00012-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef408d8810f183952adfaa816b2560a096f0abfaa71a5e8d27dc256d7ef727e0
+size 4913814182

model-00013-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96d826bd17aceaef9fb04f6399bad992cac3113a69ae6c0fcdbecc4ca58bc127
+size 4986018433

model-00014-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9b37126d375e81558ad82da3b13b8884871defb3afadf72f670c5c1adebed2c
+size 4992457818

model-00015-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d15dfc5ba0b524aa232010ad8ad93531f0e333a749ffd8c4d353e674aec67324
+size 4992457831

model-00016-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ae0da60e597d319b4bf7eb5964f7691488ac858fd6d9e1173e259f290a12c29
+size 4992457831

model-00017-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b196d3bfe354e7943cd7e4b7df0ebd97c1c2a9655cb1255894fd697f51b19dde
+size 4992457831

model-00018-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e98d254f090756ac038b577c8c74b7e6b84594bb9e4cd67dcfa5670144ccc31
+size 4992457831

model-00019-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ea97e6561ce7846ecd5cc4665bbdc8d7f4e6ca868aba2314d639a0fc2bdde4f
+size 4992457831

model-00020-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95b0f562da7cfc6c76021276414f031f14d60440c7625e99638d7e77c2defc43
+size 4992457831

model-00021-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea4cc3ed947ed7b6a0fbf44224b5321504a52b00bb546bb2ba733c8bcacb5f06
+size 4913814182

model-00022-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c637c3a293cd337d61e072220bc7b3add0a8f6fbe146cdbd6f06dba482723a8e
+size 4986018433

model-00023-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af57de8b509ac281ca2e0f44dab40c80c599da2d5f0b983627e0eead8419db83
+size 4992457818

model-00024-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6bb20249efd752d731689843d44fdffd67143b6a38c126c913502bfcabd19fa
+size 4992457831

model-00025-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b479481783608d15500e98f661df5ea2a9e76de64b6ef6e7edac06f4fad4351a
+size 4992457831

model-00026-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b09e38c735c105d53b20326b60aeeffa902bd5787eabab08840b78c833b56e72
+size 4992457831

model-00027-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffcd268cfb2627f28591fade32a75ee645a9685d1abad6a56e8f0e59ec4601e7
+size 4992457831

model-00028-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:078a008efc4d2ee6ec7531b44a88134452d492cdfb3e7265896b0fbc71e188c0
+size 4992457831

model-00029-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb889f88bc2926bf2363c23ec9283c0b3df757dcf8f53bf7d2686b3f4cb7793f
+size 4992457831

model-00030-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2918cc7fb0ed106d479430bc3f74d3831b473a86a60078fa31fb5941d515b40
+size 4913814182

model-00031-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ced59fd3cf22cfe026f291af6f434bc70f5b5ce1599f3cb432bb656166b8f1ac
+size 4986018433

model-00032-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33b23b5a60913dd1d49750b67767573cd636e730e38c2ba9d4c1fb7eb78bedc9
+size 4992457818

model-00033-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a9d5585840e43775d9643fd34dd5bafbfe04b01bc061e1c1ffdf4301679161e
+size 4992457831

model-00034-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d48b7a22ed9ded39421ebea6eba9dbe0b6cc1c32e9a9083f1cc20e9de7b6e876
+size 4992457831

model-00035-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dcfd26fb610d11f65cddca971637729413ea3325da47463397d47130865f81a
+size 4992457831

model-00036-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beacf32349a6c13b4cb1fa2cc2a1f627c8ecb5c4d6b3743dc8d5bc4a74957ac4
+size 4992457831

model-00037-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17e37706aa7186c4ef75826f447090f9bfebaabc41cbdb40753d333b9032475a
+size 4992457831

model-00038-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bb7cc0d0918a2730f66a96fb5e513f054bbcf67d88f41b89b29d5e2de176343
+size 4992457831

model-00039-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ba3f657e339c5da5a15dcc4c6e892eb9f7d4aaff22bbf6c588a8730628019e0
+size 4913814182

model-00040-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efd82016e19376d9743b36dd3693b3956edda3586a0567d726b72bb58380db7c
+size 4986018433

model-00041-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:990ceb748e37b51cd7fb7dcc4081373a883b4cf5a007df2fde176b136006958f
+size 4992457818

model-00042-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9425cc80346df15ff801c39274de1a7d125c4ca40959d0cef06c6475397ae3f
+size 4992457831

model-00043-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36a65571eabb79a8f2bbadff3764fb0db6a410dafa40d9aae0e9ed6d7c39489f
+size 4992457831

model-00044-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd38ad84194e23c569918051e575762f433a7f15ddd8fb49ac4a2060c9ac98a0
+size 4992457831

model-00045-of-00102.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03d77c81d173adccbe8ca9c86db3cf41527e2e4005ba3398b3857cbe00d50637
+size 4992457831