Text Generation
MLX
Safetensors
nemotron_h
creative-writing
philosophy
esoterica
speculative-decoding
5-bit
conversational
custom_code
Instructions to use disinfozone/kenosistron with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use disinfozone/kenosistron 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("disinfozone/kenosistron") 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 disinfozone/kenosistron with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "disinfozone/kenosistron"
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": "disinfozone/kenosistron" } ] } } }Run Pi
# Start Pi in your project directory: pi
- OpenClaw new
How to use disinfozone/kenosistron with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "disinfozone/kenosistron"
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 "disinfozone/kenosistron" \ --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 disinfozone/kenosistron with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "disinfozone/kenosistron"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "disinfozone/kenosistron" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "disinfozone/kenosistron", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use disinfozone/kenosistron 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 "disinfozone/kenosistron"
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 disinfozone/kenosistron
Run Hermes
hermes
| { | |
| "architectures": [ | |
| "NemotronHForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_nemotron_h.NemotronHConfig", | |
| "AutoModelForCausalLM": "modeling_nemotron_h.NemotronHForCausalLM" | |
| }, | |
| "bos_token_id": 1, | |
| "chunk_size": 128, | |
| "conv_kernel": 4, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 2, | |
| "expand": 2, | |
| "head_dim": 128, | |
| "hidden_dropout": 0.0, | |
| "hidden_size": 4096, | |
| "hybrid_override_pattern": "MEMEMEM*EMEMEMEM*EMEMEMEM*EMEMEMEMEM*EMEMEMEMEM*EMEMEMEMEM*EMEMEMEMEM*EMEMEMEM*EMEMEMEME", | |
| "initializer_range": 0.02, | |
| "intermediate_size": 2688, | |
| "layer_norm_epsilon": 1e-05, | |
| "mamba_head_dim": 64, | |
| "mamba_hidden_act": "silu", | |
| "mamba_num_heads": 128, | |
| "mamba_proj_bias": false, | |
| "mamba_ssm_cache_dtype": "float32", | |
| "max_position_embeddings": 262144, | |
| "mlp_bias": false, | |
| "mlp_hidden_act": "relu2", | |
| "model_type": "nemotron_h", | |
| "moe_intermediate_size": 2688, | |
| "moe_latent_size": 1024, | |
| "moe_shared_expert_intermediate_size": 5376, | |
| "moe_shared_expert_overlap": false, | |
| "mtp_hybrid_override_pattern": "*E", | |
| "n_group": 1, | |
| "n_groups": 8, | |
| "n_routed_experts": 512, | |
| "n_shared_experts": 1, | |
| "norm_eps": 1e-05, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 32, | |
| "num_experts_per_tok": 22, | |
| "num_hidden_layers": 88, | |
| "num_key_value_heads": 2, | |
| "num_logits_to_keep": 1, | |
| "num_nextn_predict_layers": 1, | |
| "pad_token_id": 0, | |
| "partial_rotary_factor": 1.0, | |
| "rescale_prenorm_residual": true, | |
| "residual_in_fp32": false, | |
| "rope_theta": 10000, | |
| "routed_scaling_factor": 5.0, | |
| "sliding_window": null, | |
| "ssm_state_size": 128, | |
| "tie_word_embeddings": false, | |
| "time_step_floor": 0.0001, | |
| "time_step_max": 0.1, | |
| "time_step_min": 0.001, | |
| "topk_group": 1, | |
| "transformers_version": "4.57.6", | |
| "use_bias": false, | |
| "use_cache": true, | |
| "use_conv_bias": true, | |
| "use_mamba_kernels": true, | |
| "vocab_size": 131072, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 5, | |
| "mode": "affine", | |
| "backbone.embeddings": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.0.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.0.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.1.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.1.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.1.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.1.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.2.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.2.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.3.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.3.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.3.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.3.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.4.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.4.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.5.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.5.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.5.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.5.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.6.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.6.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.7.mixer.k_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.7.mixer.o_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.7.mixer.q_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.7.mixer.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.8.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.8.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.8.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.8.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.9.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.9.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.10.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.10.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.10.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.10.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.11.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.11.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.12.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.12.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.12.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.12.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.13.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.13.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.14.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.14.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.14.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.14.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.15.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.15.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.16.mixer.k_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.16.mixer.o_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.16.mixer.q_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.16.mixer.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.17.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.17.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.17.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.17.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.18.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.18.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.19.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.19.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.19.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.19.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.20.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.20.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.21.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.21.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.21.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.21.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.22.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.22.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.23.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.23.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.23.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.23.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.24.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.24.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.25.mixer.k_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.25.mixer.o_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.25.mixer.q_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.25.mixer.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.26.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.26.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.26.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.26.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.27.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.27.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.28.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.28.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.28.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.28.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.29.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.29.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.30.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.30.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.30.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.30.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.31.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.31.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.32.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.32.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.32.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.32.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.33.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.33.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.34.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.34.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.34.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.34.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.35.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.35.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.36.mixer.k_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.36.mixer.o_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.36.mixer.q_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.36.mixer.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.37.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.37.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.37.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.37.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.38.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.38.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.39.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.39.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.39.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.39.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.40.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.40.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.41.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.41.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.41.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.41.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.42.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.42.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.43.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.43.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.43.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.43.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.44.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.44.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.45.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.45.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.45.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.45.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.46.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.46.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.47.mixer.k_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.47.mixer.o_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.47.mixer.q_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.47.mixer.v_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.48.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.48.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.48.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.48.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.49.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.49.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.50.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.50.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.50.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.50.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.51.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.51.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.52.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.52.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.52.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.52.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.53.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.53.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.54.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.54.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.54.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.54.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.55.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.55.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.56.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.56.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.56.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.56.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.57.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.57.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.58.mixer.k_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.58.mixer.o_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.58.mixer.q_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.58.mixer.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.59.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.59.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.59.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.59.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.60.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.60.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.61.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.61.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.61.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.61.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.62.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.62.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.63.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.63.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.63.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.63.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.64.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.64.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.65.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.65.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.65.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.65.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.66.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.66.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.67.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.67.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.67.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.67.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.68.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.68.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.69.mixer.k_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.69.mixer.o_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.69.mixer.q_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.69.mixer.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.70.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.70.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.70.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.70.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.71.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.71.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.72.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.72.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.72.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.72.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.73.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.73.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.74.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.74.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.74.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.74.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.75.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.75.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.76.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.76.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.76.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.76.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.77.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.77.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.78.mixer.k_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.78.mixer.o_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.78.mixer.q_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.78.mixer.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.79.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.79.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.79.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.79.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.80.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.80.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.81.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.81.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.81.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.81.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.82.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.82.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.83.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.83.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.83.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.83.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.84.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.84.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.85.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.85.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.85.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.85.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.86.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.86.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.87.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.87.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.87.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.87.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "lm_head": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "mtp.layers.0.mixer.k_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "mtp.layers.0.mixer.o_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "mtp.layers.0.mixer.q_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "mtp.layers.0.mixer.v_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "mtp.layers.1.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "mtp.layers.1.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "mtp.layers.1.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "mtp.layers.1.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| } | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 5, | |
| "mode": "affine", | |
| "backbone.embeddings": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.0.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.0.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.1.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.1.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.1.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.1.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.2.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.2.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.3.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.3.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.3.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.3.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.4.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.4.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.5.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.5.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.5.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.5.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.6.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.6.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.7.mixer.k_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.7.mixer.o_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.7.mixer.q_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.7.mixer.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.8.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.8.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.8.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.8.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.9.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.9.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.10.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.10.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.10.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.10.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.11.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.11.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.12.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.12.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.12.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.12.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.13.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.13.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.14.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.14.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.14.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.14.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.15.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.15.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.16.mixer.k_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.16.mixer.o_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.16.mixer.q_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.16.mixer.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.17.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.17.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.17.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.17.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.18.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.18.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.19.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.19.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.19.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.19.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.20.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.20.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.21.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.21.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.21.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.21.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.22.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.22.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.23.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.23.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.23.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.23.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.24.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.24.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.25.mixer.k_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.25.mixer.o_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.25.mixer.q_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.25.mixer.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.26.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.26.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.26.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.26.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.27.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.27.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.28.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.28.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.28.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.28.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.29.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.29.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.30.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.30.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.30.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.30.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.31.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.31.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.32.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.32.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.32.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.32.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.33.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.33.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.34.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.34.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.34.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.34.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.35.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.35.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.36.mixer.k_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.36.mixer.o_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.36.mixer.q_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.36.mixer.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.37.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.37.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.37.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.37.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.38.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.38.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.39.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.39.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.39.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.39.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.40.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.40.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.41.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.41.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.41.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.41.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.42.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.42.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.43.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.43.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.43.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.43.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.44.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.44.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.45.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.45.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.45.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.45.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.46.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.46.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.47.mixer.k_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.47.mixer.o_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.47.mixer.q_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.47.mixer.v_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.48.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.48.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.48.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.48.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.49.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.49.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.50.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.50.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.50.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.50.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.51.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.51.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.52.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.52.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.52.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.52.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.53.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.53.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.54.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.54.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.54.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.54.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.55.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.55.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.56.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.56.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.56.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.56.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.57.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.57.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.58.mixer.k_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.58.mixer.o_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.58.mixer.q_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.58.mixer.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.59.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.59.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.59.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.59.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.60.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.60.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.61.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.61.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.61.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.61.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.62.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.62.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.63.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.63.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.63.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.63.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.64.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.64.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.65.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.65.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.65.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.65.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.66.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.66.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.67.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.67.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.67.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.67.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.68.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.68.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.69.mixer.k_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.69.mixer.o_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.69.mixer.q_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.69.mixer.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.70.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.70.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.70.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.70.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.71.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.71.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.72.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.72.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.72.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.72.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.73.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.73.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.74.mixer.fc1_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.74.mixer.fc2_latent_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.74.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.74.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.75.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.75.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.76.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.76.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.76.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.76.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.77.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.77.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.78.mixer.k_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.78.mixer.o_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.78.mixer.q_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.78.mixer.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.79.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.79.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.79.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.79.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.80.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.80.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.81.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.81.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.81.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.81.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.82.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.82.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.83.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.83.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.83.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.83.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.84.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.84.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.85.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.85.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.85.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.85.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.86.mixer.in_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.86.mixer.out_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.87.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.87.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.87.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "backbone.layers.87.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "lm_head": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "mtp.layers.0.mixer.k_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "mtp.layers.0.mixer.o_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "mtp.layers.0.mixer.q_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "mtp.layers.0.mixer.v_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "mtp.layers.1.mixer.fc1_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "mtp.layers.1.mixer.fc2_latent_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "mtp.layers.1.mixer.shared_experts.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "mtp.layers.1.mixer.shared_experts.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| } | |
| } | |
| } |