Text Generation
MLX
Safetensors
English
qwen3_5
apple-silicon
speculative-decoding
mtp
multi-token-prediction
qwen3
qwen
mtplx
conversational
4-bit precision
Instructions to use Youssofal/Qwen3.6-27B-MTPLX-Optimized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Youssofal/Qwen3.6-27B-MTPLX-Optimized 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("Youssofal/Qwen3.6-27B-MTPLX-Optimized") 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
- LM Studio
- Pi new
How to use Youssofal/Qwen3.6-27B-MTPLX-Optimized with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "Youssofal/Qwen3.6-27B-MTPLX-Optimized"
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Youssofal/Qwen3.6-27B-MTPLX-Optimized" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use Youssofal/Qwen3.6-27B-MTPLX-Optimized with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "Youssofal/Qwen3.6-27B-MTPLX-Optimized"
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default Youssofal/Qwen3.6-27B-MTPLX-Optimized
Run Hermes
hermes
- MLX LM
How to use Youssofal/Qwen3.6-27B-MTPLX-Optimized with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "Youssofal/Qwen3.6-27B-MTPLX-Optimized"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "Youssofal/Qwen3.6-27B-MTPLX-Optimized" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "messages": [ {"role": "user", "content": "Hello"} ] }'
| { | |
| "architectures": [ | |
| "Qwen3_5ForConditionalGeneration" | |
| ], | |
| "eos_token_id": [ | |
| 248046, | |
| 248044 | |
| ], | |
| "image_token_id": 248056, | |
| "language_model_only": false, | |
| "library_name": "mlx", | |
| "mlx_lm_extra_tensors": { | |
| "mtp_file": "mtp.safetensors", | |
| "mtp_tensor_count": 15 | |
| }, | |
| "model_type": "qwen3_5", | |
| "mtplx_mtp_quantization": { | |
| "bits": 4, | |
| "description": "Load calibrated CyanKiwi MTP layer linears as packed MLX INT4; keep mtp.fc and MTP norms BF16.", | |
| "group_size": 32, | |
| "mode": "affine", | |
| "policy": "cyankiwi", | |
| "prequantized": true | |
| }, | |
| "mtplx_policy": { | |
| "awq_calibrated": false, | |
| "base_trunk": "models/Qwen3.6-27B-MTPLX-GDN8-Speed4", | |
| "description": "GDN8-Speed4 trunk with calibrated CyanKiwi prequantized INT4 MTP sidecar; sidecar-only ablation for committed-history acceptance.", | |
| "main_policy": "mtplx-gdn8-speed4", | |
| "mtp_policy": "cyankiwi-calibrated-int4-prequantized", | |
| "mtp_sidecar_source": "models/Qwen3.6-27B-MTPLX-CyanKiwi-Packed-BF16-INT4-v3", | |
| "name": "mtplx-gdn8-speed4-cyankiwi-mtp", | |
| "quantization_family": "mlx-affine-mixed-precision", | |
| "source": "Qwen/Qwen3.6-27B", | |
| "source_sha": "6a9e13bd6fc8f0983b9b99948120bc37f49c13e9" | |
| }, | |
| "quantization": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "language_model.lm_head": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.embed_tokens": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.32.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.32.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.32.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.32.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.32.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.32.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.32.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.32.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.33.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.33.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.33.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.33.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.33.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.33.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.33.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.33.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.34.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.34.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.34.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.34.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.34.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.34.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.34.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.34.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.35.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.35.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.35.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.35.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.35.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.35.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.35.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.36.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.36.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.36.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.36.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.36.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.36.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.36.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.36.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.37.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.37.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.37.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.37.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.37.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.37.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.37.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.37.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.38.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.38.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.38.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.38.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.38.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.38.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.38.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.38.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.39.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.39.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.39.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.39.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.39.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.39.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.39.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.40.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.40.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.40.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.40.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.40.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.40.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.40.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.40.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.41.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.41.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.41.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.41.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.41.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.41.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.41.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.41.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.42.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.42.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.42.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.42.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.42.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.42.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.42.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.42.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.43.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.43.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.43.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.43.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.43.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.43.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.43.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.44.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.44.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.44.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.44.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.44.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.44.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.44.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.44.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.45.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.45.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.45.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.45.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.45.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.45.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.45.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.45.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.46.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.46.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.46.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.46.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.46.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.46.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.46.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.46.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.47.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.47.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.47.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.47.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.47.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.47.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.47.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.48.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.48.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.48.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.48.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.48.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.48.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.48.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.48.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.49.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.49.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.49.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.49.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.49.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.49.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.49.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.49.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.50.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.50.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.50.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.50.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.50.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.50.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.50.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.50.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.51.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.51.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.51.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.51.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.51.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.51.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.51.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.52.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.52.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.52.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.52.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.52.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.52.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.52.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.52.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.53.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.53.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.53.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.53.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.53.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.53.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.53.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.53.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.54.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.54.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.54.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.54.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.54.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.54.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.54.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.54.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.55.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.55.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.55.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.55.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.55.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.55.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.55.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.56.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.56.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.56.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.56.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.56.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.56.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.56.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.56.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.57.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.57.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.57.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.57.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.57.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.57.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.57.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.57.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.58.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.58.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.58.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.58.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.58.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.58.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.58.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.58.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.59.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.59.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.59.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.59.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.59.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.59.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.59.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.60.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.60.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.60.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.60.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.60.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.60.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.60.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.60.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.61.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.61.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.61.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.61.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.61.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.61.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.61.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.61.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.62.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.62.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.62.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.62.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.62.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.62.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.62.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.62.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.63.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.63.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.63.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.63.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.63.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.63.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.63.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "mode": "affine" | |
| }, | |
| "quantization_config": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "language_model.lm_head": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.embed_tokens": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.32.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.32.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.32.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.32.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.32.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.32.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.32.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.32.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.33.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.33.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.33.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.33.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.33.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.33.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.33.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.33.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.34.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.34.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.34.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.34.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.34.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.34.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.34.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.34.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.35.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.35.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.35.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.35.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.35.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.35.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.35.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.36.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.36.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.36.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.36.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.36.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.36.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.36.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.36.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.37.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.37.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.37.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.37.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.37.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.37.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.37.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.37.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.38.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.38.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.38.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.38.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.38.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.38.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.38.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.38.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.39.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.39.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.39.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.39.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.39.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.39.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.39.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.40.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.40.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.40.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.40.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.40.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.40.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.40.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.40.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.41.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.41.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.41.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.41.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.41.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.41.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.41.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.41.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.42.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.42.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.42.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.42.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.42.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.42.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.42.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.42.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.43.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.43.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.43.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.43.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.43.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.43.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.43.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.44.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.44.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.44.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.44.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.44.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.44.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.44.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.44.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.45.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.45.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.45.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.45.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.45.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.45.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.45.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.45.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.46.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.46.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.46.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.46.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.46.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.46.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.46.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.46.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.47.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.47.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.47.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.47.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.47.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.47.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.47.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.48.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.48.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.48.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.48.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.48.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.48.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.48.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.48.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.49.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.49.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.49.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.49.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.49.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.49.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.49.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.49.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.50.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.50.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.50.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.50.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.50.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.50.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.50.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.50.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.51.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.51.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.51.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.51.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.51.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.51.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.51.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.52.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.52.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.52.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.52.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.52.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.52.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.52.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.52.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.53.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.53.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.53.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.53.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.53.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.53.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.53.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.53.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.54.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.54.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.54.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.54.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.54.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.54.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.54.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.54.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.55.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.55.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.55.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.55.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.55.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.55.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.55.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.56.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.56.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.56.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.56.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.56.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.56.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.56.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.56.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.57.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.57.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.57.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.57.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.57.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.57.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.57.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.57.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.58.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.58.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.58.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.58.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.58.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.58.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.58.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.58.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.59.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.59.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.59.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.59.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.59.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.59.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.59.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.60.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.60.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.60.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.60.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.60.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.60.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.60.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.60.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.61.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.61.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.61.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.61.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.61.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.61.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.61.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.61.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.62.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.62.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.62.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.62.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.62.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.62.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.62.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.62.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.63.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.63.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.63.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.63.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.63.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.63.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.63.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.self_attn.k_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.self_attn.o_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.self_attn.q_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.self_attn.v_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.linear_attn.in_proj_a": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.linear_attn.in_proj_b": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.linear_attn.in_proj_qkv": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.linear_attn.in_proj_z": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.linear_attn.out_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.mlp.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.mlp.gate_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "mode": "affine" | |
| }, | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_output_gate": true, | |
| "bos_token_id": 248044, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 248044, | |
| "full_attention_interval": 4, | |
| "head_dim": 256, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 17408, | |
| "layer_types": [ | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention" | |
| ], | |
| "linear_conv_kernel_dim": 4, | |
| "linear_key_head_dim": 128, | |
| "linear_num_key_heads": 16, | |
| "linear_num_value_heads": 48, | |
| "linear_value_head_dim": 128, | |
| "mamba_ssm_dtype": "float32", | |
| "max_position_embeddings": 262144, | |
| "model_type": "qwen3_5_text", | |
| "mtp_num_hidden_layers": 1, | |
| "mtp_use_dedicated_embeddings": false, | |
| "num_attention_heads": 24, | |
| "num_hidden_layers": 64, | |
| "num_key_value_heads": 4, | |
| "output_gate_type": "swish", | |
| "pad_token_id": null, | |
| "partial_rotary_factor": 0.25, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 11, | |
| 11, | |
| 10 | |
| ], | |
| "partial_rotary_factor": 0.25, | |
| "rope_theta": 10000000, | |
| "rope_type": "default" | |
| }, | |
| "tie_word_embeddings": false, | |
| "use_cache": true, | |
| "vocab_size": 248320 | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.57.1", | |
| "video_token_id": 248057, | |
| "vision_config": { | |
| "deepstack_visual_indexes": [], | |
| "depth": 27, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "in_channels": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4304, | |
| "model_type": "qwen3_5", | |
| "num_heads": 16, | |
| "num_position_embeddings": 2304, | |
| "out_hidden_size": 5120, | |
| "patch_size": 16, | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 2 | |
| }, | |
| "vision_end_token_id": 248054, | |
| "vision_start_token_id": 248053 | |
| } | |