Text Generation
MLX
Safetensors
mistral
apple-silicon
quantized
mixed-precision
axquant
axq
development
mistral-devstral
4bit
4-bit precision
conversational
Instructions to use AutomatosX/AX-Devstral-Small-2505-MLX-AXQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use AutomatosX/AX-Devstral-Small-2505-MLX-AXQ-4bit with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("AutomatosX/AX-Devstral-Small-2505-MLX-AXQ-4bit") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use AutomatosX/AX-Devstral-Small-2505-MLX-AXQ-4bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "AutomatosX/AX-Devstral-Small-2505-MLX-AXQ-4bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "AutomatosX/AX-Devstral-Small-2505-MLX-AXQ-4bit" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AutomatosX/AX-Devstral-Small-2505-MLX-AXQ-4bit", "messages": [ {"role": "user", "content": "Hello"} ] }'
| { | |
| "schema_version": "ax.native_model.v1", | |
| "model_family": "mistral3", | |
| "tensor_format": "safetensors", | |
| "layer_count": 40, | |
| "hidden_size": 5120, | |
| "intermediate_size": 32768, | |
| "attention_head_count": 32, | |
| "attention_head_dim": 128, | |
| "kv_head_count": 8, | |
| "vocab_size": 131072, | |
| "tie_word_embeddings": false, | |
| "rope_theta": 1000000000, | |
| "no_rope_layer_interval": 0, | |
| "intermediate_size_mlp": 0, | |
| "attn_output_gate": false, | |
| "rms_norm_eps": 0.00001, | |
| "moe_norm_topk_prob": false, | |
| "hidden_size_per_layer_input": 0, | |
| "tensors": [ | |
| { | |
| "name": "model.norm.weight", | |
| "role": "final_norm", | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 21855, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "lm_head.weight", | |
| "role": "lm_head", | |
| "dtype": "bf16", | |
| "shape": [ | |
| 131072, | |
| 5120 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 999517535, | |
| "length_bytes": 1342177280 | |
| }, | |
| { | |
| "name": "model.embed_tokens.weight", | |
| "role": "token_embedding", | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "shape": [ | |
| 131072, | |
| 1280 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 4340263059, | |
| "length_bytes": 671088640 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 0, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 4238026899, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.0.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 0, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3996342419, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 0, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3450888339, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.0.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 0, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 5281534099, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 0, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3483175059, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 0, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3593439379, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.0.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 0, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 4146757779, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.0.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 0, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3259195539, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.0.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 0, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3614410899, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 1, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 4123000979, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.1.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 1, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3890655379, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 1, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 4004216979, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.1.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 1, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2165635219, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 1, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 4136272019, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 1, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3793488019, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.1.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 1, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 5197648019, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.1.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 1, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3698296979, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.1.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 1, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2480238739, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 2, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3493660819, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.2.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 2, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3880159379, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 2, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3351109779, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.2.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 2, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2143178899, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 2, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3596060819, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 2, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 1834832019, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.2.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 2, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3163840659, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.2.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 2, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2048807059, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.2.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 2, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3496937619, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 3, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 4337641619, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.3.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 3, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2638682259, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 3, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3463995539, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.3.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 3, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 5190920339, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 3, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3152535699, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 3, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3611789459, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.3.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 3, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2946742419, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.3.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 3, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3030628499, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.3.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 3, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2250514579, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 4, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2932959379, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.4.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 4, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2909028499, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 4, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3980449939, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.4.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 4, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2621960339, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 4, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 1948373139, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 4, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2919688339, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.4.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 4, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2639511699, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.4.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 4, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 5106378899, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.4.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 4, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2723397779, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 5, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2602299539, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.5.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 5, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2362755219, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 5, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2564124819, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.5.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 5, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3126474899, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 5, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2143189139, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 5, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2594435219, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.5.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 5, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2368008339, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.5.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 5, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3361595539, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.5.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 5, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3896563859, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 6, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2337841299, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.6.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 6, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2935591059, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 6, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2922473619, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.6.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 6, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3477266579, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 6, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2346360979, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 6, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 1710805139, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.6.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 6, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 4253755539, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.6.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 6, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 1964757139, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.6.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 6, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 5012007059, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 7, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2334400659, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.7.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 7, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 1616423059, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 7, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 1818939539, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.7.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 7, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2362744979, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 7, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2132693139, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 7, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3461374099, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.7.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 7, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 1621676179, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.7.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 7, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 1723912339, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.7.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 7, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2165645459, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 8, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2591813779, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.8.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 8, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 1322483859, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 8, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 1597089939, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.8.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 8, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 1322473619, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 8, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2909038739, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 8, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 1612818579, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.8.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 8, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 1411623059, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.8.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 8, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 1511893139, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.8.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 8, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 1322494099, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 9, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3148275859, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.9.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 9, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 924168339, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 9, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 1134712979, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.9.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 9, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 924158099, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 9, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 4125622419, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 9, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3343081619, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.9.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 9, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 945313939, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.9.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 9, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 1039685779, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.9.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 9, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 1238587539, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 10, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 910887059, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.10.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 10, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 718528659, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 10, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 900073619, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.10.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 10, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2935580819, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 10, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 913672339, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 10, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 4240648339, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.10.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 10, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3796273299, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.10.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 10, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 815532179, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.10.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 10, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 718538899, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 11, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 1229412499, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.11.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 11, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 614305939, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 11, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 614971539, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.11.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 11, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 4236705939, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 11, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2574610579, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 11, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 631191699, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.11.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 11, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 633813139, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.11.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 11, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 2807283859, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.11.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 11, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 1145362579, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 12, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 600543379, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.12.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 12, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 292677779, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 12, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 503058579, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.12.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 12, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 718518419, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 12, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 603820179, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 12, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 513708179, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.12.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 12, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 4014702739, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.12.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 12, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 418517139, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.12.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 12, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 313659539, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 13, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 290056339, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.13.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 13, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 95076499, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 13, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 1808453779, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.13.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 13, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 95066259, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 13, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 1123571859, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 13, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 807667859, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.13.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 13, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 105572499, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.13.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 13, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 205187219, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.13.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 13, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 516329619, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 14, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 4120379539, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.14.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 14, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4871991063, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 14, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 408031379, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.14.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 14, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4377317143, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 14, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 303173779, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 14, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 3474645139, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.14.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 14, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 1864487059, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.14.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 14, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00001-of-00003.safetensors", | |
| "offset_bytes": 10524819, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.14.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 14, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4877244183, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 15, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 5089744663, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.15.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 15, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 5093021463, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 15, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4823975703, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.15.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 15, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2948673303, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 15, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4366831383, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 15, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 5127110423, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.15.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 15, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2490074903, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.15.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 15, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3689803543, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.15.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 15, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1933469463, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 16, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4150388503, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.16.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 16, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3260194583, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 16, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4671594263, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.16.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 16, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4063860503, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 16, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4690609943, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 16, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4063880983, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.16.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 16, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2747641623, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.16.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 16, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4395513623, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.16.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 16, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4274906903, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 17, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4569358103, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.17.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 17, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4063870743, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 17, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3054708503, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.17.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 17, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3780898583, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 17, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 5095653143, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 17, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2718150423, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.17.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 17, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4066502423, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.17.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 17, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4158908183, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.17.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 17, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3788773143, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 18, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3686526743, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.18.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 18, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3287074583, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 18, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4577222423, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.18.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 18, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4682080023, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 18, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3591499543, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 18, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3587567383, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.18.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 18, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4485461783, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.18.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 18, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3386863383, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.18.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 18, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3292491543, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 19, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3070457623, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.19.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 19, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3065204503, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 19, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4839714583, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.19.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 19, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3065194263, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 19, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3270690583, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 19, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3254624023, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.19.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 19, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3979974423, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.19.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 19, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3162208023, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.19.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 19, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3483856663, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 20, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2940808983, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.20.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 20, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3249207063, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 20, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2924588823, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.20.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 20, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2286882583, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 20, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3044222743, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 20, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2954100503, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.20.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 20, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2839392023, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.20.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 20, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3078321943, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.20.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 20, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4739106583, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 21, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2679156503, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.21.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 21, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2289196823, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 21, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2573960983, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.21.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 21, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2289186583, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 21, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2702421783, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 21, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2836770583, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.21.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 21, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3885766423, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.21.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 21, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 5130551063, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.21.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 21, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2294613783, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 22, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3786151703, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.22.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 22, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4834461463, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 22, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4264421143, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.22.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 22, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2017355543, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 22, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4974073623, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 22, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4687333143, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.22.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 22, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2107969303, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.22.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 22, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2191855383, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.22.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 22, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2023264023, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 23, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3475992343, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.23.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 23, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1716852503, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 23, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1917413143, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.23.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 23, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1805991703, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 23, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4723377943, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 23, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3257409303, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.23.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 23, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3602640663, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.23.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 23, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1830250263, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.23.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 23, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 5224922903, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 24, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 5093031703, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.24.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 24, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2679146263, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 24, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1522046743, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.24.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 24, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1149136663, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 24, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1706366743, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 24, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3883144983, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.24.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 24, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1335269143, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.24.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 24, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1437505303, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.24.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 24, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1238275863, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 25, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2693738263, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.25.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 25, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 834553623, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 25, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1107848983, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.25.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 25, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 834543383, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 25, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1138650903, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 25, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1124069143, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.25.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 25, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 5000451863, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.25.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 25, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1023307543, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.25.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 25, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 918449943, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 26, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3568070423, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.26.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 26, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 649885463, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 26, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3577081623, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.26.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 26, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 649875223, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 26, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2378663703, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 26, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1434883863, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.26.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 26, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 749510423, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.26.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 26, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1716862743, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.26.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 26, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 655138583, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 27, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1914136343, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.27.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 27, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2953926423, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 27, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 628739863, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.27.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 27, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 522397463, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 27, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 639389463, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 27, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1332647703, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.27.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 27, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 538300183, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.27.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 27, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1154389783, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.27.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 27, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1621661463, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.28.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 28, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3246094103, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.28.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 28, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3044212503, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.28.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 28, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4984559383, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.28.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 28, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4569347863, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.28.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 28, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1128165143, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.28.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 28, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3040935703, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.28.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 28, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 434415383, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.28.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 28, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4587708183, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.28.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 28, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 345286423, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.29.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 29, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 3969652503, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.29.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 29, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 215351063, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.29.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 29, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 5111381783, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.29.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 29, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 4358792983, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.29.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 29, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 324314903, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.29.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 29, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 320874263, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.29.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 29, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 225847063, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.29.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 29, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2406188823, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.29.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 29, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1532532503, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.30.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 30, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1811244823, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.30.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 30, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 11687703, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.30.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 30, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 201096983, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.30.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 30, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 11677463, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.30.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 30, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1012821783, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.30.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 30, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 211746583, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.30.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 30, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2595260183, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.30.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 30, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 116555543, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.30.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 30, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 16940823, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.31.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 31, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 8400663, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.31.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 31, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 3782944095, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.31.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 31, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2276396823, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.31.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 31, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2629080415, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.31.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 31, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 1419155223, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.31.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 31, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 208663, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.31.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 31, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 2956885783, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.31.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 31, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00002-of-00003.safetensors", | |
| "offset_bytes": 834563863, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.31.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 31, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 3878636895, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.32.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 32, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 3627930975, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.32.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 32, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 3050876255, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.32.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 32, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 3647591775, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.32.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 32, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2966979935, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.32.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 32, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2576969055, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.32.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 32, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 722290015, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.32.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 32, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 638383455, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.32.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 32, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2629090655, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.32.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 32, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 3140015455, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.33.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 33, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2939454815, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.33.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 33, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2812601695, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.33.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 33, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2901740895, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.33.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 33, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2728705375, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.33.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 33, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2610730335, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.33.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 33, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2917479775, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.33.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 33, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2812611935, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.33.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 33, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 3523073375, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.33.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 33, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 3399538015, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.34.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 34, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2346937695, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.34.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 34, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2939444575, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.34.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 34, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 3868151135, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.34.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 34, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2595974495, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.34.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 34, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2712976735, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.34.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 34, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2608108895, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.34.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 34, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2483907935, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.34.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 34, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 3056129375, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.34.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 34, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 3223901535, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.35.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 35, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2457365855, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.35.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 35, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 722279775, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.35.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 35, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 3489977695, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.35.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 35, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 722269535, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.35.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 35, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2349559135, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.35.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 35, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2341694815, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.35.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 35, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2360044895, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.35.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 35, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 814368095, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.35.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 35, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 730482015, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.36.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 36, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 3606959455, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.36.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 36, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 3663975775, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.36.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 36, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2944697695, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.36.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 36, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2939434335, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.36.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 36, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 982150495, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.36.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 36, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 632157535, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.36.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 36, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 3665296735, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.36.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 36, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 547943775, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.36.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 36, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2728715615, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.37.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 37, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2444258655, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.37.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 37, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 982140255, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.37.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 37, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2597623135, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.37.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 37, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2912226655, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.37.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 37, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 3755081055, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.37.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 37, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2574347615, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.37.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 37, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 3782954335, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.37.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 37, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 427674975, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.37.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 37, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2966990175, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.38.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 38, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2476043615, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.38.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 38, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 512871775, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.38.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 38, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 2928948575, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.38.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 38, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 201237855, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.38.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 38, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 308399455, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.38.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 38, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 334613855, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.38.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 38, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 898254175, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.38.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 38, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 342478175, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.38.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 38, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 201248095, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.39.self_attn.k_proj.weight", | |
| "role": "attention_k", | |
| "layer_index": 39, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 3614823775, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.39.input_layernorm.weight", | |
| "role": "attention_norm", | |
| "layer_index": 39, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 3772775775, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.39.self_attn.o_proj.weight", | |
| "role": "attention_o", | |
| "layer_index": 39, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 512 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 295947615, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.39.post_attention_layernorm.weight", | |
| "role": "attention_post_norm", | |
| "layer_index": 39, | |
| "dtype": "bf16", | |
| "shape": [ | |
| 5120 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 32095, | |
| "length_bytes": 10240 | |
| }, | |
| { | |
| "name": "model.layers.39.self_attn.q_proj.weight", | |
| "role": "attention_q", | |
| "layer_index": 39, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 4096, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 185509215, | |
| "length_bytes": 10485760 | |
| }, | |
| { | |
| "name": "model.layers.39.self_attn.v_proj.weight", | |
| "role": "attention_v", | |
| "layer_index": 39, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 32, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 1024, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 545322335, | |
| "length_bytes": 2621440 | |
| }, | |
| { | |
| "name": "model.layers.39.mlp.down_proj.weight", | |
| "role": "ffn_down", | |
| "layer_index": 39, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 5120, | |
| 4096 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 3310409055, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.39.mlp.gate_proj.weight", | |
| "role": "ffn_gate", | |
| "layer_index": 39, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 15770975, | |
| "length_bytes": 83886080 | |
| }, | |
| { | |
| "name": "model.layers.39.mlp.up_proj.weight", | |
| "role": "ffn_up", | |
| "layer_index": 39, | |
| "dtype": "u32", | |
| "source_quantized": true, | |
| "quantization": { | |
| "mode": "affine", | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "shape": [ | |
| 32768, | |
| 640 | |
| ], | |
| "file": "model-00003-of-00003.safetensors", | |
| "offset_bytes": 99657055, | |
| "length_bytes": 83886080 | |
| } | |
| ] | |
| } |