Instructions to use acbdkk/Qwen3.5-4B-Coding with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use acbdkk/Qwen3.5-4B-Coding 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("acbdkk/Qwen3.5-4B-Coding") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Unsloth Studio
How to use acbdkk/Qwen3.5-4B-Coding with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for acbdkk/Qwen3.5-4B-Coding to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for acbdkk/Qwen3.5-4B-Coding to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for acbdkk/Qwen3.5-4B-Coding to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="acbdkk/Qwen3.5-4B-Coding", max_seq_length=2048, ) - Pi
How to use acbdkk/Qwen3.5-4B-Coding with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "acbdkk/Qwen3.5-4B-Coding"
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": "acbdkk/Qwen3.5-4B-Coding" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use acbdkk/Qwen3.5-4B-Coding 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 "acbdkk/Qwen3.5-4B-Coding"
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 acbdkk/Qwen3.5-4B-Coding
Run Hermes
hermes
- OpenClaw new
How to use acbdkk/Qwen3.5-4B-Coding with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "acbdkk/Qwen3.5-4B-Coding"
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "acbdkk/Qwen3.5-4B-Coding" \ --custom-provider-id mlx-lm \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
- MLX LM
How to use acbdkk/Qwen3.5-4B-Coding with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "acbdkk/Qwen3.5-4B-Coding"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "acbdkk/Qwen3.5-4B-Coding" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "acbdkk/Qwen3.5-4B-Coding", "messages": [ {"role": "user", "content": "Hello"} ] }'
| { | |
| "base_model_name_or_path": "unsloth/Qwen3.5-4B", | |
| "base_model_revision": "b85e62a1372ca32d6a37c81bccf70ad2cf8f779e", | |
| "base_model_commit_hash": "b85e62a1372ca32d6a37c81bccf70ad2cf8f779e", | |
| "base_quantization_config": { | |
| "language_model.model.layers.0.linear_attn.in_proj_qkv": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.linear_attn.in_proj_z": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.linear_attn.in_proj_b": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.linear_attn.in_proj_a": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.linear_attn.out_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.linear_attn.in_proj_qkv": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.linear_attn.in_proj_z": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.linear_attn.in_proj_b": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.linear_attn.in_proj_a": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.linear_attn.out_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.linear_attn.in_proj_qkv": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.linear_attn.in_proj_z": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.linear_attn.in_proj_b": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.linear_attn.in_proj_a": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.linear_attn.out_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.linear_attn.in_proj_qkv": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.linear_attn.in_proj_z": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.linear_attn.in_proj_b": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.linear_attn.in_proj_a": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.linear_attn.out_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.linear_attn.in_proj_qkv": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.linear_attn.in_proj_z": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.linear_attn.in_proj_b": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.linear_attn.in_proj_a": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.linear_attn.out_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.linear_attn.in_proj_qkv": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.linear_attn.in_proj_z": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.linear_attn.in_proj_b": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.linear_attn.in_proj_a": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.linear_attn.out_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.linear_attn.in_proj_qkv": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.linear_attn.in_proj_z": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.linear_attn.in_proj_b": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.linear_attn.in_proj_a": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.linear_attn.out_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.linear_attn.in_proj_qkv": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.linear_attn.in_proj_z": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.linear_attn.in_proj_b": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.linear_attn.in_proj_a": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.linear_attn.out_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.linear_attn.in_proj_qkv": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.linear_attn.in_proj_z": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.linear_attn.in_proj_b": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.linear_attn.in_proj_a": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.linear_attn.out_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.linear_attn.in_proj_qkv": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.linear_attn.in_proj_z": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.linear_attn.in_proj_b": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.linear_attn.in_proj_a": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.linear_attn.out_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.linear_attn.in_proj_qkv": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.linear_attn.in_proj_z": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.linear_attn.in_proj_b": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.linear_attn.in_proj_a": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.linear_attn.out_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.linear_attn.in_proj_qkv": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.linear_attn.in_proj_z": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.linear_attn.in_proj_b": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.linear_attn.in_proj_a": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.linear_attn.out_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.linear_attn.in_proj_qkv": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.linear_attn.in_proj_z": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.linear_attn.in_proj_b": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.linear_attn.in_proj_a": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.linear_attn.out_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.linear_attn.in_proj_qkv": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.linear_attn.in_proj_z": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.linear_attn.in_proj_b": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.linear_attn.in_proj_a": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.linear_attn.out_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.linear_attn.in_proj_qkv": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.linear_attn.in_proj_z": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.linear_attn.in_proj_b": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.linear_attn.in_proj_a": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.linear_attn.out_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.linear_attn.in_proj_qkv": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.linear_attn.in_proj_z": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.linear_attn.in_proj_b": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.linear_attn.in_proj_a": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.linear_attn.out_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.linear_attn.in_proj_qkv": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.linear_attn.in_proj_z": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.linear_attn.in_proj_b": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.linear_attn.in_proj_a": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.linear_attn.out_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.linear_attn.in_proj_qkv": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.linear_attn.in_proj_z": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.linear_attn.in_proj_b": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.linear_attn.in_proj_a": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.linear_attn.out_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.linear_attn.in_proj_qkv": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.linear_attn.in_proj_z": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.linear_attn.in_proj_b": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.linear_attn.in_proj_a": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.linear_attn.out_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.linear_attn.in_proj_qkv": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.linear_attn.in_proj_z": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.linear_attn.in_proj_b": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.linear_attn.in_proj_a": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.linear_attn.out_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.linear_attn.in_proj_qkv": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.linear_attn.in_proj_z": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.linear_attn.in_proj_b": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.linear_attn.in_proj_a": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.linear_attn.out_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.linear_attn.in_proj_qkv": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.linear_attn.in_proj_z": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.linear_attn.in_proj_b": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.linear_attn.in_proj_a": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.linear_attn.out_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.linear_attn.in_proj_qkv": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.linear_attn.in_proj_z": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.linear_attn.in_proj_b": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.linear_attn.in_proj_a": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.linear_attn.out_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.linear_attn.in_proj_qkv": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.linear_attn.in_proj_z": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.linear_attn.in_proj_b": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.linear_attn.in_proj_a": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.linear_attn.out_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| } | |
| }, | |
| "base_quantization_policy": { | |
| "enabled": true, | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine", | |
| "source": "load_in_4bit", | |
| "quantize_modules": null, | |
| "has_callable_predicate": false, | |
| "force_requantize": false | |
| }, | |
| "base_quantized_source": "runtime", | |
| "base_resolved_quantization_map": { | |
| "language_model.model.layers.0.linear_attn.in_proj_qkv": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.linear_attn.in_proj_z": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.linear_attn.in_proj_b": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.linear_attn.in_proj_a": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.linear_attn.out_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.down_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_qkv": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.linear_attn.in_proj_z": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.linear_attn.in_proj_b": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.linear_attn.in_proj_a": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.linear_attn.out_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.down_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.2.linear_attn.in_proj_qkv": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.linear_attn.in_proj_z": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.linear_attn.in_proj_b": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.linear_attn.in_proj_a": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.linear_attn.out_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.down_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.3.self_attn.q_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.v_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.mlp.gate_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.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.linear_attn.in_proj_qkv": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.linear_attn.in_proj_z": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.linear_attn.in_proj_b": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.linear_attn.in_proj_a": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.linear_attn.out_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.down_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.5.linear_attn.in_proj_qkv": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.linear_attn.in_proj_z": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.linear_attn.in_proj_b": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.linear_attn.in_proj_a": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.linear_attn.out_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.down_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.6.linear_attn.in_proj_qkv": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.linear_attn.in_proj_z": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.linear_attn.in_proj_b": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.linear_attn.in_proj_a": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.linear_attn.out_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.down_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.7.self_attn.q_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.v_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.mlp.gate_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.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.linear_attn.in_proj_qkv": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.linear_attn.in_proj_z": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.linear_attn.in_proj_b": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.linear_attn.in_proj_a": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.linear_attn.out_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.down_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_qkv": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.linear_attn.in_proj_z": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.linear_attn.in_proj_b": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.linear_attn.in_proj_a": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.linear_attn.out_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.down_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.mlp.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.linear_attn.in_proj_qkv": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.linear_attn.in_proj_z": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.linear_attn.in_proj_b": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.linear_attn.in_proj_a": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.linear_attn.out_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.down_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.self_attn.q_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.v_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.mlp.gate_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.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.linear_attn.in_proj_qkv": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.linear_attn.in_proj_z": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.linear_attn.in_proj_b": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.linear_attn.in_proj_a": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.linear_attn.out_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.down_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_qkv": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.linear_attn.in_proj_z": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.linear_attn.in_proj_b": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.linear_attn.in_proj_a": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.linear_attn.out_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.down_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_qkv": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.linear_attn.in_proj_z": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.linear_attn.in_proj_b": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.linear_attn.in_proj_a": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.linear_attn.out_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.down_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.self_attn.q_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.v_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.mlp.gate_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.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.linear_attn.in_proj_qkv": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.linear_attn.in_proj_z": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.linear_attn.in_proj_b": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.linear_attn.in_proj_a": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.linear_attn.out_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.down_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_qkv": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.linear_attn.in_proj_z": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.linear_attn.in_proj_b": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.linear_attn.in_proj_a": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.linear_attn.out_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.down_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_qkv": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.linear_attn.in_proj_z": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.linear_attn.in_proj_b": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.linear_attn.in_proj_a": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.linear_attn.out_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.down_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.self_attn.q_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.v_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.mlp.gate_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.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.linear_attn.in_proj_qkv": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.linear_attn.in_proj_z": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.linear_attn.in_proj_b": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.linear_attn.in_proj_a": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.linear_attn.out_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.down_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_qkv": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.linear_attn.in_proj_z": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.linear_attn.in_proj_b": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.linear_attn.in_proj_a": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.linear_attn.out_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.down_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_qkv": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.linear_attn.in_proj_z": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.linear_attn.in_proj_b": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.linear_attn.in_proj_a": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.linear_attn.out_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.down_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.self_attn.q_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.v_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.mlp.gate_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.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.linear_attn.in_proj_qkv": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.linear_attn.in_proj_z": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.linear_attn.in_proj_b": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.linear_attn.in_proj_a": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.linear_attn.out_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.down_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_qkv": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.linear_attn.in_proj_z": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.linear_attn.in_proj_b": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.linear_attn.in_proj_a": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.linear_attn.out_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.down_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_qkv": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.linear_attn.in_proj_z": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.linear_attn.in_proj_b": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.linear_attn.in_proj_a": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.linear_attn.out_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.down_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.self_attn.q_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.v_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.mlp.gate_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.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.linear_attn.in_proj_qkv": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.linear_attn.in_proj_z": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.linear_attn.in_proj_b": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.linear_attn.in_proj_a": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.linear_attn.out_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.down_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_qkv": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.linear_attn.in_proj_z": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.linear_attn.in_proj_b": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.linear_attn.in_proj_a": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.linear_attn.out_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.down_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.30.linear_attn.in_proj_qkv": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.linear_attn.in_proj_z": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.linear_attn.in_proj_b": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.linear_attn.in_proj_a": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.linear_attn.out_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.down_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.self_attn.q_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.v_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.mlp.gate_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.up_proj": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine" | |
| } | |
| }, | |
| "requires_unsloth_mlx_runtime_quantization": true, | |
| "unsloth_mlx_lora_module_paths": [ | |
| "language_model.model.layers.31.mlp.up_proj", | |
| "language_model.model.layers.31.mlp.down_proj", | |
| "language_model.model.layers.31.mlp.gate_proj", | |
| "language_model.model.layers.31.self_attn.o_proj", | |
| "language_model.model.layers.31.self_attn.v_proj", | |
| "language_model.model.layers.31.self_attn.k_proj", | |
| "language_model.model.layers.31.self_attn.q_proj", | |
| "language_model.model.layers.30.mlp.up_proj", | |
| "language_model.model.layers.30.mlp.down_proj", | |
| "language_model.model.layers.30.mlp.gate_proj", | |
| "language_model.model.layers.30.linear_attn.out_proj", | |
| "language_model.model.layers.29.mlp.up_proj", | |
| "language_model.model.layers.29.mlp.down_proj", | |
| "language_model.model.layers.29.mlp.gate_proj", | |
| "language_model.model.layers.29.linear_attn.out_proj", | |
| "language_model.model.layers.28.mlp.up_proj", | |
| "language_model.model.layers.28.mlp.down_proj", | |
| "language_model.model.layers.28.mlp.gate_proj", | |
| "language_model.model.layers.28.linear_attn.out_proj", | |
| "language_model.model.layers.27.mlp.up_proj", | |
| "language_model.model.layers.27.mlp.down_proj", | |
| "language_model.model.layers.27.mlp.gate_proj", | |
| "language_model.model.layers.27.self_attn.o_proj", | |
| "language_model.model.layers.27.self_attn.v_proj", | |
| "language_model.model.layers.27.self_attn.k_proj", | |
| "language_model.model.layers.27.self_attn.q_proj", | |
| "language_model.model.layers.26.mlp.up_proj", | |
| "language_model.model.layers.26.mlp.down_proj", | |
| "language_model.model.layers.26.mlp.gate_proj", | |
| "language_model.model.layers.26.linear_attn.out_proj", | |
| "language_model.model.layers.25.mlp.up_proj", | |
| "language_model.model.layers.25.mlp.down_proj", | |
| "language_model.model.layers.25.mlp.gate_proj", | |
| "language_model.model.layers.25.linear_attn.out_proj", | |
| "language_model.model.layers.24.mlp.up_proj", | |
| "language_model.model.layers.24.mlp.down_proj", | |
| "language_model.model.layers.24.mlp.gate_proj", | |
| "language_model.model.layers.24.linear_attn.out_proj", | |
| "language_model.model.layers.23.mlp.up_proj", | |
| "language_model.model.layers.23.mlp.down_proj", | |
| "language_model.model.layers.23.mlp.gate_proj", | |
| "language_model.model.layers.23.self_attn.o_proj", | |
| "language_model.model.layers.23.self_attn.v_proj", | |
| "language_model.model.layers.23.self_attn.k_proj", | |
| "language_model.model.layers.23.self_attn.q_proj", | |
| "language_model.model.layers.22.mlp.up_proj", | |
| "language_model.model.layers.22.mlp.down_proj", | |
| "language_model.model.layers.22.mlp.gate_proj", | |
| "language_model.model.layers.22.linear_attn.out_proj", | |
| "language_model.model.layers.21.mlp.up_proj", | |
| "language_model.model.layers.21.mlp.down_proj", | |
| "language_model.model.layers.21.mlp.gate_proj", | |
| "language_model.model.layers.21.linear_attn.out_proj", | |
| "language_model.model.layers.20.mlp.up_proj", | |
| "language_model.model.layers.20.mlp.down_proj", | |
| "language_model.model.layers.20.mlp.gate_proj", | |
| "language_model.model.layers.20.linear_attn.out_proj", | |
| "language_model.model.layers.19.mlp.up_proj", | |
| "language_model.model.layers.19.mlp.down_proj", | |
| "language_model.model.layers.19.mlp.gate_proj", | |
| "language_model.model.layers.19.self_attn.o_proj", | |
| "language_model.model.layers.19.self_attn.v_proj", | |
| "language_model.model.layers.19.self_attn.k_proj", | |
| "language_model.model.layers.19.self_attn.q_proj", | |
| "language_model.model.layers.18.mlp.up_proj", | |
| "language_model.model.layers.18.mlp.down_proj", | |
| "language_model.model.layers.18.mlp.gate_proj", | |
| "language_model.model.layers.18.linear_attn.out_proj", | |
| "language_model.model.layers.17.mlp.up_proj", | |
| "language_model.model.layers.17.mlp.down_proj", | |
| "language_model.model.layers.17.mlp.gate_proj", | |
| "language_model.model.layers.17.linear_attn.out_proj", | |
| "language_model.model.layers.16.mlp.up_proj", | |
| "language_model.model.layers.16.mlp.down_proj", | |
| "language_model.model.layers.16.mlp.gate_proj", | |
| "language_model.model.layers.16.linear_attn.out_proj", | |
| "language_model.model.layers.15.mlp.up_proj", | |
| "language_model.model.layers.15.mlp.down_proj", | |
| "language_model.model.layers.15.mlp.gate_proj", | |
| "language_model.model.layers.15.self_attn.o_proj", | |
| "language_model.model.layers.15.self_attn.v_proj", | |
| "language_model.model.layers.15.self_attn.k_proj", | |
| "language_model.model.layers.15.self_attn.q_proj", | |
| "language_model.model.layers.14.mlp.up_proj", | |
| "language_model.model.layers.14.mlp.down_proj", | |
| "language_model.model.layers.14.mlp.gate_proj", | |
| "language_model.model.layers.14.linear_attn.out_proj", | |
| "language_model.model.layers.13.mlp.up_proj", | |
| "language_model.model.layers.13.mlp.down_proj", | |
| "language_model.model.layers.13.mlp.gate_proj", | |
| "language_model.model.layers.13.linear_attn.out_proj", | |
| "language_model.model.layers.12.mlp.up_proj", | |
| "language_model.model.layers.12.mlp.down_proj", | |
| "language_model.model.layers.12.mlp.gate_proj", | |
| "language_model.model.layers.12.linear_attn.out_proj", | |
| "language_model.model.layers.11.mlp.up_proj", | |
| "language_model.model.layers.11.mlp.down_proj", | |
| "language_model.model.layers.11.mlp.gate_proj", | |
| "language_model.model.layers.11.self_attn.o_proj", | |
| "language_model.model.layers.11.self_attn.v_proj", | |
| "language_model.model.layers.11.self_attn.k_proj", | |
| "language_model.model.layers.11.self_attn.q_proj", | |
| "language_model.model.layers.10.mlp.up_proj", | |
| "language_model.model.layers.10.mlp.down_proj", | |
| "language_model.model.layers.10.mlp.gate_proj", | |
| "language_model.model.layers.10.linear_attn.out_proj", | |
| "language_model.model.layers.9.mlp.up_proj", | |
| "language_model.model.layers.9.mlp.down_proj", | |
| "language_model.model.layers.9.mlp.gate_proj", | |
| "language_model.model.layers.9.linear_attn.out_proj", | |
| "language_model.model.layers.8.mlp.up_proj", | |
| "language_model.model.layers.8.mlp.down_proj", | |
| "language_model.model.layers.8.mlp.gate_proj", | |
| "language_model.model.layers.8.linear_attn.out_proj", | |
| "language_model.model.layers.7.mlp.up_proj", | |
| "language_model.model.layers.7.mlp.down_proj", | |
| "language_model.model.layers.7.mlp.gate_proj", | |
| "language_model.model.layers.7.self_attn.o_proj", | |
| "language_model.model.layers.7.self_attn.v_proj", | |
| "language_model.model.layers.7.self_attn.k_proj", | |
| "language_model.model.layers.7.self_attn.q_proj", | |
| "language_model.model.layers.6.mlp.up_proj", | |
| "language_model.model.layers.6.mlp.down_proj", | |
| "language_model.model.layers.6.mlp.gate_proj", | |
| "language_model.model.layers.6.linear_attn.out_proj", | |
| "language_model.model.layers.5.mlp.up_proj", | |
| "language_model.model.layers.5.mlp.down_proj", | |
| "language_model.model.layers.5.mlp.gate_proj", | |
| "language_model.model.layers.5.linear_attn.out_proj", | |
| "language_model.model.layers.4.mlp.up_proj", | |
| "language_model.model.layers.4.mlp.down_proj", | |
| "language_model.model.layers.4.mlp.gate_proj", | |
| "language_model.model.layers.4.linear_attn.out_proj", | |
| "language_model.model.layers.3.mlp.up_proj", | |
| "language_model.model.layers.3.mlp.down_proj", | |
| "language_model.model.layers.3.mlp.gate_proj", | |
| "language_model.model.layers.3.self_attn.o_proj", | |
| "language_model.model.layers.3.self_attn.v_proj", | |
| "language_model.model.layers.3.self_attn.k_proj", | |
| "language_model.model.layers.3.self_attn.q_proj", | |
| "language_model.model.layers.2.mlp.up_proj", | |
| "language_model.model.layers.2.mlp.down_proj", | |
| "language_model.model.layers.2.mlp.gate_proj", | |
| "language_model.model.layers.2.linear_attn.out_proj", | |
| "language_model.model.layers.1.mlp.up_proj", | |
| "language_model.model.layers.1.mlp.down_proj", | |
| "language_model.model.layers.1.mlp.gate_proj", | |
| "language_model.model.layers.1.linear_attn.out_proj", | |
| "language_model.model.layers.0.mlp.up_proj", | |
| "language_model.model.layers.0.mlp.down_proj", | |
| "language_model.model.layers.0.mlp.gate_proj", | |
| "language_model.model.layers.0.linear_attn.out_proj" | |
| ] | |
| } |