Text Generation
MLX
Safetensors
hy_v3
mixture-of-experts
apple-silicon
conversational
4-bit precision
Instructions to use avlp12/Hy3-Alis-MLX-Dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use avlp12/Hy3-Alis-MLX-Dynamic 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("avlp12/Hy3-Alis-MLX-Dynamic") 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
- Pi
How to use avlp12/Hy3-Alis-MLX-Dynamic with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "avlp12/Hy3-Alis-MLX-Dynamic"
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": "avlp12/Hy3-Alis-MLX-Dynamic" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use avlp12/Hy3-Alis-MLX-Dynamic 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 "avlp12/Hy3-Alis-MLX-Dynamic"
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 avlp12/Hy3-Alis-MLX-Dynamic
Run Hermes
hermes
- OpenClaw new
How to use avlp12/Hy3-Alis-MLX-Dynamic with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "avlp12/Hy3-Alis-MLX-Dynamic"
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 "avlp12/Hy3-Alis-MLX-Dynamic" \ --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 avlp12/Hy3-Alis-MLX-Dynamic with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "avlp12/Hy3-Alis-MLX-Dynamic"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "avlp12/Hy3-Alis-MLX-Dynamic" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "avlp12/Hy3-Alis-MLX-Dynamic", "messages": [ {"role": "user", "content": "Hello"} ] }'
| { | |
| "architectures": [ | |
| "HYV3ForCausalLM" | |
| ], | |
| "bos_token_id": 120000, | |
| "enable_attention_fp32_softmax": false, | |
| "enable_lm_head_fp32": true, | |
| "enable_moe_fp32_combine": false, | |
| "eod_token_id": 120026, | |
| "eos_token_id": 120025, | |
| "expert_hidden_dim": 1536, | |
| "first_k_dense_replace": 1, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.006, | |
| "intermediate_size": 13312, | |
| "max_position_embeddings": 262144, | |
| "model_type": "hy_v3", | |
| "moe_intermediate_size": 1536, | |
| "moe_router_enable_expert_bias": true, | |
| "moe_router_use_sigmoid": true, | |
| "num_attention_heads": 64, | |
| "num_experts": 192, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 80, | |
| "num_key_value_heads": 8, | |
| "num_nextn_predict_layers": 1, | |
| "num_shared_experts": 1, | |
| "output_router_logits": true, | |
| "pad_token_id": 120002, | |
| "qk_norm": true, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine", | |
| "model.embed_tokens": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.2.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.2.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.2.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.2.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.2.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.2.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.2.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.2.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.2.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.2.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.3.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.3.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.3.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.3.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.3.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.3.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.3.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.3.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.3.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.3.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.4.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.4.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.4.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.4.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.4.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.4.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.4.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.4.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.4.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.4.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.5.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.5.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.5.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.5.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.5.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.5.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.5.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.5.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.5.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.5.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.6.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.6.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.6.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.6.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.6.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.6.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.6.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.6.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.6.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.6.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.7.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.7.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.7.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.7.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.7.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.7.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.7.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.7.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.7.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.7.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.8.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.8.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.8.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.8.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.8.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.8.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.8.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.8.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.8.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.8.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.9.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.9.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.9.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.9.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.9.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.9.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.9.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.9.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.9.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.9.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.13.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.13.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.13.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.13.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.13.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.13.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.13.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.13.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.13.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.13.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.14.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.14.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.14.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.14.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.14.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.14.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.14.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.14.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.14.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.14.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.15.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.15.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.15.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.15.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.15.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.15.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.15.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.15.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.15.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.15.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.16.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.16.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.16.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.16.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.16.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.16.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.16.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.16.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.16.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.16.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.17.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.17.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.17.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.17.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.17.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.17.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.17.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.17.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.17.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.17.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.18.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.18.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.18.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.18.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.18.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.18.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.18.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.18.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.18.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.18.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.19.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.19.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.19.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.19.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.19.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.19.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.19.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.19.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.19.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.19.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.20.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.20.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.20.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.20.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.20.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.20.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.20.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.20.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.20.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.20.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.21.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.21.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.21.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.21.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.21.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.21.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.21.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.21.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.21.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.21.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.22.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.22.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.22.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.22.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.22.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.22.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.22.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.22.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.22.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.22.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.23.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.23.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.23.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.23.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.23.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.23.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.23.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.23.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.23.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.23.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.24.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.24.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.24.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.24.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.24.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.24.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.24.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.24.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.24.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.24.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.25.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.25.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.25.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.25.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.25.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.25.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.25.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.25.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.25.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.25.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.26.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.26.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.26.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.26.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.26.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.26.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.26.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.26.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.26.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.26.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.27.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.27.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.27.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.27.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.27.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.27.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.27.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.27.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.27.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.27.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.28.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.28.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.28.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.28.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.28.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.28.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.28.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.28.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.28.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.28.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.29.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.29.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.29.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.29.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.29.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.29.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.29.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.29.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.29.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.29.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.30.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.30.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.30.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.30.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.30.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.30.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.30.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.30.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.30.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.30.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.31.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.31.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.31.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.31.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.31.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.31.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.31.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.31.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.31.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.31.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.32.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.32.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.32.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.32.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.32.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.32.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.32.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.32.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.32.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.32.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.33.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.33.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.33.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.33.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.33.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.33.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.33.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.33.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.33.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.33.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.34.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.34.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.34.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.34.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.34.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.34.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.34.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.34.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.34.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.34.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.35.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.35.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.35.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.35.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.35.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.35.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.35.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.35.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.35.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.35.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.36.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.36.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.36.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.36.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.36.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.36.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.36.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.36.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.36.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.36.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.37.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.37.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.37.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.37.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.37.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.37.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.37.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.37.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.37.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.37.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.38.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.38.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.38.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.38.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.38.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.38.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.38.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.38.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.38.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.38.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.39.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.39.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.39.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.39.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.39.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.39.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.39.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.39.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.39.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.39.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.40.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.40.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.40.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.40.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.40.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.40.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.40.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.40.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.40.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.40.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.41.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.41.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.41.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.41.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.41.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.41.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.41.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.41.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.41.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.41.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.42.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.42.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.42.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.42.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.42.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.42.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.42.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.42.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.42.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.42.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.43.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.43.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.43.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.43.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.43.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.43.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.43.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.43.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.43.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.43.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.44.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.44.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.44.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.44.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.44.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.44.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.44.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.44.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.44.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.44.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.45.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.45.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.45.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.45.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.45.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.45.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.45.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.45.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.45.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.45.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.46.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.46.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.46.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.46.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.46.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.46.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.46.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.46.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.46.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.46.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.47.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.47.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.47.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.47.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.47.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.47.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.47.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.47.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.47.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.47.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.48.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.48.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.48.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.48.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.48.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.48.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.48.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.48.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.48.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.48.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.49.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.49.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.49.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.49.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.49.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.49.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.49.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.49.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.49.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.49.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.50.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.50.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.50.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.50.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.50.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.50.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.50.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.50.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.50.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.50.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.51.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.51.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.51.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.51.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.51.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.51.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.51.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.51.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.51.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.51.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.52.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.52.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.52.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.52.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.52.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.52.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.52.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.52.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.52.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.52.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.53.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.53.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.53.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.53.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.53.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.53.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.53.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.53.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.53.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.53.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.54.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.54.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.54.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.54.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.54.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.54.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.54.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.54.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.54.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.54.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.55.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.55.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.55.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.55.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.55.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.55.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.55.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.55.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.55.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.55.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.56.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.56.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.56.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.56.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.56.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.56.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.56.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.56.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.56.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.56.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.57.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.57.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.57.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.57.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.57.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.57.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.57.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.57.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.57.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.57.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.58.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.58.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.58.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.58.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.58.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.58.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.58.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.58.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.58.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.58.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.59.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.59.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.59.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.59.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.59.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.59.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.59.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.59.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.59.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.59.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.60.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.60.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.60.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.60.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.60.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.60.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.60.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.60.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.60.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.60.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.61.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.61.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.61.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.61.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.61.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.61.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.61.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.61.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.61.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.61.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.64.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.64.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.64.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.64.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.64.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.64.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.64.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.64.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.64.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.64.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.65.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.65.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.65.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.65.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.65.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.65.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.65.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.65.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.65.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.65.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.66.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.66.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.66.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.66.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.66.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.66.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.66.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.66.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.66.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.66.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.67.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.67.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.67.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.67.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.67.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.67.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.67.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.67.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.67.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.67.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.68.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.68.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.68.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.68.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.68.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.68.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.68.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.68.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.68.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.68.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.69.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.69.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.69.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.69.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.69.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.69.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.69.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.69.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.69.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.69.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.70.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.70.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.70.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.70.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.70.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.70.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.70.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.70.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.70.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.70.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.71.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.71.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.71.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.71.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.71.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.71.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.71.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.71.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.71.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.71.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.72.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.72.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.72.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.72.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.72.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.72.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.72.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.72.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.72.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.72.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.73.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.73.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.73.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.73.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.73.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.73.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.73.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.73.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.73.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.73.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.74.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.74.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.74.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.74.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.74.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.74.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.74.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.74.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.74.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.74.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.75.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.75.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.75.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.75.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.75.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.75.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.75.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.75.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.75.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.75.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.76.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.76.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.76.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.76.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.76.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.76.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.76.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.76.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.76.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.76.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.77.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.77.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.77.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.77.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.77.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.77.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.77.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.77.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.77.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.77.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.78.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.78.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.78.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.78.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.78.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.78.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.78.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.78.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.78.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.78.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.79.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.79.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.79.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.79.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.79.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.79.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.79.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.79.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.79.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.79.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "lm_head": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| } | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine", | |
| "model.embed_tokens": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.2.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.2.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.2.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.2.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.2.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.2.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.2.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.2.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.2.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.2.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.3.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.3.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.3.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.3.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.3.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.3.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.3.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.3.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.3.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.3.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.4.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.4.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.4.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.4.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.4.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.4.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.4.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.4.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.4.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.4.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.5.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.5.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.5.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.5.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.5.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.5.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.5.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.5.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.5.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.5.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.6.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.6.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.6.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.6.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.6.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.6.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.6.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.6.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.6.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.6.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.7.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.7.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.7.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.7.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.7.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.7.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.7.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.7.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.7.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.7.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.8.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.8.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.8.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.8.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.8.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.8.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.8.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.8.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.8.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.8.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.9.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.9.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.9.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.9.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.9.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.9.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.9.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.9.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.9.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.9.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.13.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.13.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.13.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.13.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.13.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.13.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.13.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.13.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.13.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.13.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.14.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.14.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.14.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.14.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.14.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.14.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.14.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.14.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.14.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.14.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.15.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.15.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.15.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.15.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.15.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.15.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.15.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.15.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.15.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.15.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.16.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.16.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.16.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.16.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.16.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.16.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.16.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.16.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.16.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.16.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.17.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.17.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.17.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.17.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.17.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.17.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.17.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.17.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.17.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.17.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.18.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.18.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.18.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.18.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.18.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.18.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.18.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.18.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.18.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.18.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.19.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.19.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.19.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.19.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.19.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.19.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.19.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.19.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.19.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.19.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.20.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.20.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.20.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.20.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.20.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.20.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.20.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.20.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.20.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.20.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.21.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.21.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.21.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.21.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.21.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.21.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.21.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.21.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.21.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.21.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.22.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.22.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.22.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.22.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.22.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.22.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.22.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.22.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.22.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.22.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.23.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.23.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.23.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.23.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.23.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.23.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.23.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.23.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.23.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.23.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.24.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.24.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.24.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.24.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.24.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.24.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.24.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.24.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.24.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.24.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.25.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.25.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.25.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.25.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.25.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.25.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.25.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.25.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.25.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.25.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.26.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.26.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.26.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.26.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.26.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.26.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.26.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.26.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.26.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.26.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.27.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.27.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.27.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.27.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.27.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.27.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.27.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.27.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.27.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.27.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.28.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.28.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.28.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.28.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.28.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.28.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.28.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.28.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.28.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.28.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.29.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.29.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.29.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.29.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.29.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.29.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.29.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.29.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.29.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.29.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.30.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.30.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.30.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.30.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.30.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.30.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.30.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.30.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.30.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.30.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.31.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.31.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.31.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.31.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.31.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.31.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.31.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.31.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.31.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.31.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.32.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.32.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.32.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.32.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.32.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.32.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.32.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.32.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.32.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.32.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.33.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.33.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.33.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.33.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.33.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.33.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.33.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.33.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.33.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.33.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.34.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.34.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.34.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.34.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.34.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.34.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.34.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.34.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.34.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.34.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.35.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.35.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.35.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.35.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.35.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.35.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.35.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.35.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.35.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.35.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.36.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.36.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.36.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.36.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.36.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.36.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.36.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.36.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.36.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.36.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.37.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.37.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.37.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.37.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.37.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.37.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.37.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.37.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.37.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.37.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.38.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.38.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.38.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.38.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.38.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.38.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.38.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.38.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.38.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.38.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.39.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.39.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.39.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.39.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.39.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.39.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.39.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.39.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.39.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.39.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.40.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.40.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.40.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.40.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.40.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.40.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.40.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.40.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.40.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.40.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.41.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.41.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.41.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.41.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.41.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.41.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.41.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.41.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.41.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.41.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.42.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.42.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.42.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.42.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.42.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.42.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.42.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.42.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.42.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.42.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.43.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.43.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.43.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.43.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.43.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.43.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.43.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.43.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.43.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.43.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.44.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.44.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.44.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.44.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.44.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.44.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.44.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.44.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.44.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.44.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.45.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.45.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.45.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.45.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.45.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.45.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.45.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.45.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.45.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.45.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.46.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.46.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.46.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.46.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.46.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.46.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.46.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.46.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.46.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.46.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.47.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.47.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.47.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.47.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.47.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.47.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.47.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.47.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.47.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.47.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.48.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.48.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.48.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.48.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.48.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.48.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.48.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.48.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.48.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.48.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.49.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.49.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.49.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.49.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.49.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.49.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.49.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.49.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.49.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.49.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.50.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.50.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.50.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.50.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.50.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.50.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.50.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.50.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.50.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.50.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.51.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.51.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.51.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.51.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.51.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.51.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.51.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.51.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.51.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.51.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.52.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.52.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.52.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.52.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.52.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.52.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.52.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.52.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.52.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.52.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.53.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.53.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.53.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.53.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.53.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.53.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.53.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.53.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.53.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.53.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.54.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.54.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.54.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.54.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.54.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.54.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.54.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.54.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.54.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.54.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.55.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.55.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.55.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.55.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.55.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.55.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.55.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.55.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.55.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.55.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.56.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.56.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.56.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.56.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.56.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.56.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.56.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.56.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.56.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.56.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.57.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.57.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.57.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.57.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.57.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.57.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.57.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.57.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.57.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.57.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.58.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.58.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.58.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.58.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.58.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.58.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.58.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.58.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.58.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.58.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.59.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.59.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.59.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.59.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.59.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.59.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.59.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.59.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.59.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.59.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.60.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.60.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.60.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.60.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.60.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.60.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.60.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.60.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.60.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.60.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.61.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.61.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.61.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.61.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.61.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.61.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.61.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.61.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.61.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.61.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.64.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.64.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.64.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.64.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.64.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.64.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.64.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.64.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.64.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.64.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.65.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.65.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.65.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.65.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.65.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.65.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.65.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.65.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.65.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.65.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.66.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.66.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.66.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.66.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.66.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.66.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.66.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.66.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.66.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.66.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.67.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.67.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.67.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.67.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.67.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.67.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.67.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.67.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.67.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.67.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.68.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.68.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.68.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.68.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.68.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.68.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.68.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.68.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.68.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.68.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.69.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.69.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.69.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.69.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.69.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.69.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.69.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.69.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.69.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.69.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.70.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.70.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.70.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.70.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.70.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.70.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.70.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.70.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.70.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.70.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.71.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.71.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.71.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.71.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.71.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.71.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.71.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.71.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.71.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.71.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.72.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.72.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.72.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.72.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.72.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.72.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.72.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.72.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.72.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.72.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.73.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.73.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.73.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.73.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.73.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.73.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.73.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.73.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.73.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.73.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.74.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.74.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.74.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.74.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.74.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.74.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.74.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.74.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.74.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.74.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.75.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.75.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.75.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.75.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.75.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.75.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.75.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.75.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.75.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.75.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.76.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.76.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.76.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.76.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.76.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.76.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.76.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.76.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.76.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.76.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.77.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.77.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.77.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.77.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.77.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.77.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.77.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.77.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.77.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.77.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.78.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.78.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.78.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.78.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.78.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.78.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.78.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.78.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.78.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.78.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.79.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.79.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.79.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.79.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.79.mlp.switch_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.79.mlp.switch_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.79.mlp.switch_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "model.layers.79.mlp.shared_mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.79.mlp.shared_mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "model.layers.79.mlp.shared_mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "lm_head": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| } | |
| }, | |
| "rms_norm_eps": 1e-05, | |
| "rope_parameters": { | |
| "rope_theta": 11158840.0, | |
| "rope_type": "default" | |
| }, | |
| "route_norm": true, | |
| "router_scaling_factor": 2.826, | |
| "sep_token_id": 120007, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.6.0", | |
| "use_cache": true, | |
| "use_grouped_mm": false, | |
| "vocab_size": 120832 | |
| } |