Text Generation
MLX
Safetensors
laguna
quantized
4-bit precision
imatrix
sbq
apple-silicon
conversational
custom_code
Instructions to use SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Pi
How to use SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit"
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit 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 "SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit"
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 SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit"
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 "SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit" \ --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"
| { | |
| "enabled": true, | |
| "cache_path": "/Users/grb/.omlx/models/.oqe_imatrix/Laguna-XS-2.1-bf16-oQe-s128-l512.npz", | |
| "cache_reused": false, | |
| "entry_count": 476, | |
| "calib_dataset": "oqe_code_multilingual", | |
| "collection": { | |
| "dataset": "oqe_code_multilingual", | |
| "requested_samples": 128, | |
| "seq_length": 512, | |
| "adaptive": true, | |
| "adaptive_step_samples": 128, | |
| "adaptive_max_samples": 1024, | |
| "available_samples": 1024, | |
| "micro_batch_size": 8, | |
| "micro_batches": 36, | |
| "batch_plan": { | |
| "micro_batch_size": 8, | |
| "estimated_sample_bytes": 33554432, | |
| "capture_budget_bytes": 299821555, | |
| "system_available_bytes": 102338478080, | |
| "metal_available_bytes": 96871177596, | |
| "live_available_bytes": 96871177596, | |
| "model_bytes": 66889022016, | |
| "remaining_available_bytes": 29982155580, | |
| "fits_one_sample": true, | |
| "hidden_size": 2048, | |
| "num_experts": 256, | |
| "top_k": 8, | |
| "gemma4_state_bytes": 0, | |
| "num_hidden_layers": 40, | |
| "num_kv_shared_layers": 0, | |
| "per_layer_input_size": 0 | |
| }, | |
| "processed_samples": 288, | |
| "installed_modules": 477, | |
| "capture_module_classes": { | |
| "Linear": 360, | |
| "SwitchLinear": 117 | |
| }, | |
| "switch_capture_modules": 117, | |
| "requires_expert_counts": true, | |
| "coverage_sufficient": true, | |
| "collection_sufficient": true, | |
| "coverage": { | |
| "has_expert_counts": true, | |
| "expert_modules": 117, | |
| "total_experts": 29952, | |
| "active_experts": 29952, | |
| "zero_count_experts": 0, | |
| "active_ratio": 1.0, | |
| "min_count": 1, | |
| "p05_count": 640.0, | |
| "p10_count": 981.0, | |
| "median_count": 2970.0, | |
| "max_count": 92414, | |
| "min_required_count": 16, | |
| "required_percentile": 5 | |
| }, | |
| "rounds": [ | |
| { | |
| "processed_samples": 128, | |
| "coverage_sufficient": false, | |
| "collection_sufficient": false, | |
| "coverage": { | |
| "has_expert_counts": true, | |
| "expert_modules": 117, | |
| "total_experts": 29952, | |
| "active_experts": 29946, | |
| "zero_count_experts": 6, | |
| "active_ratio": 0.9997996794871795, | |
| "min_count": 0, | |
| "p05_count": 318.0, | |
| "p10_count": 469.0, | |
| "median_count": 1379.0, | |
| "max_count": 39308, | |
| "min_required_count": 16, | |
| "required_percentile": 5 | |
| } | |
| }, | |
| { | |
| "processed_samples": 256, | |
| "coverage_sufficient": false, | |
| "collection_sufficient": false, | |
| "coverage": { | |
| "has_expert_counts": true, | |
| "expert_modules": 117, | |
| "total_experts": 29952, | |
| "active_experts": 29949, | |
| "zero_count_experts": 3, | |
| "active_ratio": 0.9998998397435898, | |
| "min_count": 0, | |
| "p05_count": 582.0, | |
| "p10_count": 880.0, | |
| "median_count": 2651.0, | |
| "max_count": 81636, | |
| "min_required_count": 16, | |
| "required_percentile": 5 | |
| } | |
| }, | |
| { | |
| "processed_samples": 288, | |
| "coverage_sufficient": true, | |
| "collection_sufficient": true, | |
| "coverage": { | |
| "has_expert_counts": true, | |
| "expert_modules": 117, | |
| "total_experts": 29952, | |
| "active_experts": 29952, | |
| "zero_count_experts": 0, | |
| "active_ratio": 1.0, | |
| "min_count": 1, | |
| "p05_count": 640.0, | |
| "p10_count": 981.0, | |
| "median_count": 2970.0, | |
| "max_count": 92414, | |
| "min_required_count": 16, | |
| "required_percentile": 5 | |
| } | |
| } | |
| ] | |
| }, | |
| "expert_coverage": { | |
| "has_expert_counts": true, | |
| "expert_modules": 117, | |
| "total_experts": 29952, | |
| "active_experts": 29952, | |
| "zero_count_experts": 0, | |
| "active_ratio": 1.0, | |
| "min_count": 1, | |
| "p05_count": 640.0, | |
| "p10_count": 981.0, | |
| "median_count": 2970.0, | |
| "max_count": 92414, | |
| "min_required_count": 16, | |
| "required_percentile": 5 | |
| }, | |
| "applied": [ | |
| "model.layers.0.mlp.down_proj", | |
| "model.layers.0.mlp.gate_proj", | |
| "model.layers.0.mlp.up_proj", | |
| "model.layers.0.self_attn.g_proj", | |
| "model.layers.0.self_attn.k_proj", | |
| "model.layers.0.self_attn.o_proj", | |
| "model.layers.0.self_attn.q_proj", | |
| "model.layers.0.self_attn.v_proj", | |
| "model.layers.1.mlp.shared_expert.down_proj", | |
| "model.layers.1.mlp.shared_expert.gate_proj", | |
| "model.layers.1.mlp.shared_expert.up_proj", | |
| "model.layers.1.mlp.switch_mlp.down_proj", | |
| "model.layers.1.mlp.switch_mlp.gate_proj", | |
| "model.layers.1.mlp.switch_mlp.up_proj", | |
| "model.layers.1.self_attn.g_proj", | |
| "model.layers.1.self_attn.k_proj", | |
| "model.layers.1.self_attn.o_proj", | |
| "model.layers.1.self_attn.q_proj", | |
| "model.layers.1.self_attn.v_proj", | |
| "model.layers.10.mlp.shared_expert.down_proj", | |
| "model.layers.10.mlp.shared_expert.gate_proj", | |
| "model.layers.10.mlp.shared_expert.up_proj", | |
| "model.layers.10.mlp.switch_mlp.down_proj", | |
| "model.layers.10.mlp.switch_mlp.gate_proj", | |
| "model.layers.10.mlp.switch_mlp.up_proj", | |
| "model.layers.10.self_attn.g_proj", | |
| "model.layers.10.self_attn.k_proj", | |
| "model.layers.10.self_attn.o_proj", | |
| "model.layers.10.self_attn.q_proj", | |
| "model.layers.10.self_attn.v_proj", | |
| "model.layers.11.mlp.shared_expert.down_proj", | |
| "model.layers.11.mlp.shared_expert.gate_proj", | |
| "model.layers.11.mlp.shared_expert.up_proj", | |
| "model.layers.11.mlp.switch_mlp.down_proj", | |
| "model.layers.11.mlp.switch_mlp.gate_proj", | |
| "model.layers.11.mlp.switch_mlp.up_proj", | |
| "model.layers.11.self_attn.g_proj", | |
| "model.layers.11.self_attn.k_proj", | |
| "model.layers.11.self_attn.o_proj", | |
| "model.layers.11.self_attn.q_proj", | |
| "model.layers.11.self_attn.v_proj", | |
| "model.layers.12.mlp.shared_expert.down_proj", | |
| "model.layers.12.mlp.shared_expert.gate_proj", | |
| "model.layers.12.mlp.shared_expert.up_proj", | |
| "model.layers.12.mlp.switch_mlp.down_proj", | |
| "model.layers.12.mlp.switch_mlp.gate_proj", | |
| "model.layers.12.mlp.switch_mlp.up_proj", | |
| "model.layers.12.self_attn.g_proj", | |
| "model.layers.12.self_attn.k_proj", | |
| "model.layers.12.self_attn.o_proj", | |
| "model.layers.12.self_attn.q_proj", | |
| "model.layers.12.self_attn.v_proj", | |
| "model.layers.13.mlp.shared_expert.down_proj", | |
| "model.layers.13.mlp.shared_expert.gate_proj", | |
| "model.layers.13.mlp.shared_expert.up_proj", | |
| "model.layers.13.mlp.switch_mlp.down_proj", | |
| "model.layers.13.mlp.switch_mlp.gate_proj", | |
| "model.layers.13.mlp.switch_mlp.up_proj", | |
| "model.layers.13.self_attn.g_proj", | |
| "model.layers.13.self_attn.k_proj", | |
| "model.layers.13.self_attn.o_proj", | |
| "model.layers.13.self_attn.q_proj", | |
| "model.layers.13.self_attn.v_proj", | |
| "model.layers.14.mlp.shared_expert.down_proj", | |
| "model.layers.14.mlp.shared_expert.gate_proj", | |
| "model.layers.14.mlp.shared_expert.up_proj", | |
| "model.layers.14.mlp.switch_mlp.down_proj", | |
| "model.layers.14.mlp.switch_mlp.gate_proj", | |
| "model.layers.14.mlp.switch_mlp.up_proj", | |
| "model.layers.14.self_attn.g_proj", | |
| "model.layers.14.self_attn.k_proj", | |
| "model.layers.14.self_attn.o_proj", | |
| "model.layers.14.self_attn.q_proj", | |
| "model.layers.14.self_attn.v_proj", | |
| "model.layers.15.mlp.shared_expert.down_proj", | |
| "model.layers.15.mlp.shared_expert.gate_proj", | |
| "model.layers.15.mlp.shared_expert.up_proj", | |
| "model.layers.15.mlp.switch_mlp.down_proj", | |
| "model.layers.15.mlp.switch_mlp.gate_proj", | |
| "model.layers.15.mlp.switch_mlp.up_proj", | |
| "model.layers.15.self_attn.g_proj", | |
| "model.layers.15.self_attn.k_proj", | |
| "model.layers.15.self_attn.o_proj", | |
| "model.layers.15.self_attn.q_proj", | |
| "model.layers.15.self_attn.v_proj", | |
| "model.layers.16.mlp.shared_expert.down_proj", | |
| "model.layers.16.mlp.shared_expert.gate_proj", | |
| "model.layers.16.mlp.shared_expert.up_proj", | |
| "model.layers.16.mlp.switch_mlp.down_proj", | |
| "model.layers.16.mlp.switch_mlp.gate_proj", | |
| "model.layers.16.mlp.switch_mlp.up_proj", | |
| "model.layers.16.self_attn.g_proj", | |
| "model.layers.16.self_attn.k_proj", | |
| "model.layers.16.self_attn.o_proj", | |
| "model.layers.16.self_attn.q_proj", | |
| "model.layers.16.self_attn.v_proj", | |
| "model.layers.17.mlp.shared_expert.down_proj", | |
| "model.layers.17.mlp.shared_expert.gate_proj", | |
| "model.layers.17.mlp.shared_expert.up_proj", | |
| "model.layers.17.mlp.switch_mlp.down_proj", | |
| "model.layers.17.mlp.switch_mlp.gate_proj", | |
| "model.layers.17.mlp.switch_mlp.up_proj", | |
| "model.layers.17.self_attn.g_proj", | |
| "model.layers.17.self_attn.k_proj", | |
| "model.layers.17.self_attn.o_proj", | |
| "model.layers.17.self_attn.q_proj", | |
| "model.layers.17.self_attn.v_proj", | |
| "model.layers.18.mlp.shared_expert.down_proj", | |
| "model.layers.18.mlp.shared_expert.gate_proj", | |
| "model.layers.18.mlp.shared_expert.up_proj", | |
| "model.layers.18.mlp.switch_mlp.down_proj", | |
| "model.layers.18.mlp.switch_mlp.gate_proj", | |
| "model.layers.18.mlp.switch_mlp.up_proj", | |
| "model.layers.18.self_attn.g_proj", | |
| "model.layers.18.self_attn.k_proj", | |
| "model.layers.18.self_attn.o_proj", | |
| "model.layers.18.self_attn.q_proj", | |
| "model.layers.18.self_attn.v_proj", | |
| "model.layers.19.mlp.shared_expert.down_proj", | |
| "model.layers.19.mlp.shared_expert.gate_proj", | |
| "model.layers.19.mlp.shared_expert.up_proj", | |
| "model.layers.19.mlp.switch_mlp.down_proj", | |
| "model.layers.19.mlp.switch_mlp.gate_proj", | |
| "model.layers.19.mlp.switch_mlp.up_proj", | |
| "model.layers.19.self_attn.g_proj", | |
| "model.layers.19.self_attn.k_proj", | |
| "model.layers.19.self_attn.o_proj", | |
| "model.layers.19.self_attn.q_proj", | |
| "model.layers.19.self_attn.v_proj", | |
| "model.layers.2.mlp.shared_expert.down_proj", | |
| "model.layers.2.mlp.shared_expert.gate_proj", | |
| "model.layers.2.mlp.shared_expert.up_proj", | |
| "model.layers.2.mlp.switch_mlp.down_proj", | |
| "model.layers.2.mlp.switch_mlp.gate_proj", | |
| "model.layers.2.mlp.switch_mlp.up_proj", | |
| "model.layers.2.self_attn.g_proj", | |
| "model.layers.2.self_attn.k_proj", | |
| "model.layers.2.self_attn.o_proj", | |
| "model.layers.2.self_attn.q_proj", | |
| "model.layers.2.self_attn.v_proj", | |
| "model.layers.20.mlp.shared_expert.down_proj", | |
| "model.layers.20.mlp.shared_expert.gate_proj", | |
| "model.layers.20.mlp.shared_expert.up_proj", | |
| "model.layers.20.mlp.switch_mlp.down_proj", | |
| "model.layers.20.mlp.switch_mlp.gate_proj", | |
| "model.layers.20.mlp.switch_mlp.up_proj", | |
| "model.layers.20.self_attn.g_proj", | |
| "model.layers.20.self_attn.k_proj", | |
| "model.layers.20.self_attn.o_proj", | |
| "model.layers.20.self_attn.q_proj", | |
| "model.layers.20.self_attn.v_proj", | |
| "model.layers.21.mlp.shared_expert.down_proj", | |
| "model.layers.21.mlp.shared_expert.gate_proj", | |
| "model.layers.21.mlp.shared_expert.up_proj", | |
| "model.layers.21.mlp.switch_mlp.down_proj", | |
| "model.layers.21.mlp.switch_mlp.gate_proj", | |
| "model.layers.21.mlp.switch_mlp.up_proj", | |
| "model.layers.21.self_attn.g_proj", | |
| "model.layers.21.self_attn.k_proj", | |
| "model.layers.21.self_attn.o_proj", | |
| "model.layers.21.self_attn.q_proj", | |
| "model.layers.21.self_attn.v_proj", | |
| "model.layers.22.mlp.shared_expert.down_proj", | |
| "model.layers.22.mlp.shared_expert.gate_proj", | |
| "model.layers.22.mlp.shared_expert.up_proj", | |
| "model.layers.22.mlp.switch_mlp.down_proj", | |
| "model.layers.22.mlp.switch_mlp.gate_proj", | |
| "model.layers.22.mlp.switch_mlp.up_proj", | |
| "model.layers.22.self_attn.g_proj", | |
| "model.layers.22.self_attn.k_proj", | |
| "model.layers.22.self_attn.o_proj", | |
| "model.layers.22.self_attn.q_proj", | |
| "model.layers.22.self_attn.v_proj", | |
| "model.layers.23.mlp.shared_expert.down_proj", | |
| "model.layers.23.mlp.shared_expert.gate_proj", | |
| "model.layers.23.mlp.shared_expert.up_proj", | |
| "model.layers.23.mlp.switch_mlp.down_proj", | |
| "model.layers.23.mlp.switch_mlp.gate_proj", | |
| "model.layers.23.mlp.switch_mlp.up_proj", | |
| "model.layers.23.self_attn.g_proj", | |
| "model.layers.23.self_attn.k_proj", | |
| "model.layers.23.self_attn.o_proj", | |
| "model.layers.23.self_attn.q_proj", | |
| "model.layers.23.self_attn.v_proj", | |
| "model.layers.24.mlp.shared_expert.down_proj", | |
| "model.layers.24.mlp.shared_expert.gate_proj", | |
| "model.layers.24.mlp.shared_expert.up_proj", | |
| "model.layers.24.mlp.switch_mlp.down_proj", | |
| "model.layers.24.mlp.switch_mlp.gate_proj", | |
| "model.layers.24.mlp.switch_mlp.up_proj", | |
| "model.layers.24.self_attn.g_proj", | |
| "model.layers.24.self_attn.k_proj", | |
| "model.layers.24.self_attn.o_proj", | |
| "model.layers.24.self_attn.q_proj", | |
| "model.layers.24.self_attn.v_proj", | |
| "model.layers.25.mlp.shared_expert.down_proj", | |
| "model.layers.25.mlp.shared_expert.gate_proj", | |
| "model.layers.25.mlp.shared_expert.up_proj", | |
| "model.layers.25.mlp.switch_mlp.down_proj", | |
| "model.layers.25.mlp.switch_mlp.gate_proj", | |
| "model.layers.25.mlp.switch_mlp.up_proj", | |
| "model.layers.25.self_attn.g_proj", | |
| "model.layers.25.self_attn.k_proj", | |
| "model.layers.25.self_attn.o_proj", | |
| "model.layers.25.self_attn.q_proj", | |
| "model.layers.25.self_attn.v_proj", | |
| "model.layers.26.mlp.shared_expert.down_proj", | |
| "model.layers.26.mlp.shared_expert.gate_proj", | |
| "model.layers.26.mlp.shared_expert.up_proj", | |
| "model.layers.26.mlp.switch_mlp.down_proj", | |
| "model.layers.26.mlp.switch_mlp.gate_proj", | |
| "model.layers.26.mlp.switch_mlp.up_proj", | |
| "model.layers.26.self_attn.g_proj", | |
| "model.layers.26.self_attn.k_proj", | |
| "model.layers.26.self_attn.o_proj", | |
| "model.layers.26.self_attn.q_proj", | |
| "model.layers.26.self_attn.v_proj", | |
| "model.layers.27.mlp.shared_expert.down_proj", | |
| "model.layers.27.mlp.shared_expert.gate_proj", | |
| "model.layers.27.mlp.shared_expert.up_proj", | |
| "model.layers.27.mlp.switch_mlp.down_proj", | |
| "model.layers.27.mlp.switch_mlp.gate_proj", | |
| "model.layers.27.mlp.switch_mlp.up_proj", | |
| "model.layers.27.self_attn.g_proj", | |
| "model.layers.27.self_attn.k_proj", | |
| "model.layers.27.self_attn.o_proj", | |
| "model.layers.27.self_attn.q_proj", | |
| "model.layers.27.self_attn.v_proj", | |
| "model.layers.28.mlp.shared_expert.down_proj", | |
| "model.layers.28.mlp.shared_expert.gate_proj", | |
| "model.layers.28.mlp.shared_expert.up_proj", | |
| "model.layers.28.mlp.switch_mlp.down_proj", | |
| "model.layers.28.mlp.switch_mlp.gate_proj", | |
| "model.layers.28.mlp.switch_mlp.up_proj", | |
| "model.layers.28.self_attn.g_proj", | |
| "model.layers.28.self_attn.k_proj", | |
| "model.layers.28.self_attn.o_proj", | |
| "model.layers.28.self_attn.q_proj", | |
| "model.layers.28.self_attn.v_proj", | |
| "model.layers.29.mlp.shared_expert.down_proj", | |
| "model.layers.29.mlp.shared_expert.gate_proj", | |
| "model.layers.29.mlp.shared_expert.up_proj", | |
| "model.layers.29.mlp.switch_mlp.down_proj", | |
| "model.layers.29.mlp.switch_mlp.gate_proj", | |
| "model.layers.29.mlp.switch_mlp.up_proj", | |
| "model.layers.29.self_attn.g_proj", | |
| "model.layers.29.self_attn.k_proj", | |
| "model.layers.29.self_attn.o_proj", | |
| "model.layers.29.self_attn.q_proj", | |
| "model.layers.29.self_attn.v_proj", | |
| "model.layers.3.mlp.shared_expert.down_proj", | |
| "model.layers.3.mlp.shared_expert.gate_proj", | |
| "model.layers.3.mlp.shared_expert.up_proj", | |
| "model.layers.3.mlp.switch_mlp.down_proj", | |
| "model.layers.3.mlp.switch_mlp.gate_proj", | |
| "model.layers.3.mlp.switch_mlp.up_proj", | |
| "model.layers.3.self_attn.g_proj", | |
| "model.layers.3.self_attn.k_proj", | |
| "model.layers.3.self_attn.o_proj", | |
| "model.layers.3.self_attn.q_proj", | |
| "model.layers.3.self_attn.v_proj", | |
| "model.layers.30.mlp.shared_expert.down_proj", | |
| "model.layers.30.mlp.shared_expert.gate_proj", | |
| "model.layers.30.mlp.shared_expert.up_proj", | |
| "model.layers.30.mlp.switch_mlp.down_proj", | |
| "model.layers.30.mlp.switch_mlp.gate_proj", | |
| "model.layers.30.mlp.switch_mlp.up_proj", | |
| "model.layers.30.self_attn.g_proj", | |
| "model.layers.30.self_attn.k_proj", | |
| "model.layers.30.self_attn.o_proj", | |
| "model.layers.30.self_attn.q_proj", | |
| "model.layers.30.self_attn.v_proj", | |
| "model.layers.31.mlp.shared_expert.down_proj", | |
| "model.layers.31.mlp.shared_expert.gate_proj", | |
| "model.layers.31.mlp.shared_expert.up_proj", | |
| "model.layers.31.mlp.switch_mlp.down_proj", | |
| "model.layers.31.mlp.switch_mlp.gate_proj", | |
| "model.layers.31.mlp.switch_mlp.up_proj", | |
| "model.layers.31.self_attn.g_proj", | |
| "model.layers.31.self_attn.k_proj", | |
| "model.layers.31.self_attn.o_proj", | |
| "model.layers.31.self_attn.q_proj", | |
| "model.layers.31.self_attn.v_proj", | |
| "model.layers.32.mlp.shared_expert.down_proj", | |
| "model.layers.32.mlp.shared_expert.gate_proj", | |
| "model.layers.32.mlp.shared_expert.up_proj", | |
| "model.layers.32.mlp.switch_mlp.down_proj", | |
| "model.layers.32.mlp.switch_mlp.gate_proj", | |
| "model.layers.32.mlp.switch_mlp.up_proj", | |
| "model.layers.32.self_attn.g_proj", | |
| "model.layers.32.self_attn.k_proj", | |
| "model.layers.32.self_attn.o_proj", | |
| "model.layers.32.self_attn.q_proj", | |
| "model.layers.32.self_attn.v_proj", | |
| "model.layers.33.mlp.shared_expert.down_proj", | |
| "model.layers.33.mlp.shared_expert.gate_proj", | |
| "model.layers.33.mlp.shared_expert.up_proj", | |
| "model.layers.33.mlp.switch_mlp.down_proj", | |
| "model.layers.33.mlp.switch_mlp.gate_proj", | |
| "model.layers.33.mlp.switch_mlp.up_proj", | |
| "model.layers.33.self_attn.g_proj", | |
| "model.layers.33.self_attn.k_proj", | |
| "model.layers.33.self_attn.o_proj", | |
| "model.layers.33.self_attn.q_proj", | |
| "model.layers.33.self_attn.v_proj", | |
| "model.layers.34.mlp.shared_expert.down_proj", | |
| "model.layers.34.mlp.shared_expert.gate_proj", | |
| "model.layers.34.mlp.shared_expert.up_proj", | |
| "model.layers.34.mlp.switch_mlp.down_proj", | |
| "model.layers.34.mlp.switch_mlp.gate_proj", | |
| "model.layers.34.mlp.switch_mlp.up_proj", | |
| "model.layers.34.self_attn.g_proj", | |
| "model.layers.34.self_attn.k_proj", | |
| "model.layers.34.self_attn.o_proj", | |
| "model.layers.34.self_attn.q_proj", | |
| "model.layers.34.self_attn.v_proj", | |
| "model.layers.35.mlp.shared_expert.down_proj", | |
| "model.layers.35.mlp.shared_expert.gate_proj", | |
| "model.layers.35.mlp.shared_expert.up_proj", | |
| "model.layers.35.mlp.switch_mlp.down_proj", | |
| "model.layers.35.mlp.switch_mlp.gate_proj", | |
| "model.layers.35.mlp.switch_mlp.up_proj", | |
| "model.layers.35.self_attn.g_proj", | |
| "model.layers.35.self_attn.k_proj", | |
| "model.layers.35.self_attn.o_proj", | |
| "model.layers.35.self_attn.q_proj", | |
| "model.layers.35.self_attn.v_proj", | |
| "model.layers.36.mlp.shared_expert.down_proj", | |
| "model.layers.36.mlp.shared_expert.gate_proj", | |
| "model.layers.36.mlp.shared_expert.up_proj", | |
| "model.layers.36.mlp.switch_mlp.down_proj", | |
| "model.layers.36.mlp.switch_mlp.gate_proj", | |
| "model.layers.36.mlp.switch_mlp.up_proj", | |
| "model.layers.36.self_attn.g_proj", | |
| "model.layers.36.self_attn.k_proj", | |
| "model.layers.36.self_attn.o_proj", | |
| "model.layers.36.self_attn.q_proj", | |
| "model.layers.36.self_attn.v_proj", | |
| "model.layers.37.mlp.shared_expert.down_proj", | |
| "model.layers.37.mlp.shared_expert.gate_proj", | |
| "model.layers.37.mlp.shared_expert.up_proj", | |
| "model.layers.37.mlp.switch_mlp.down_proj", | |
| "model.layers.37.mlp.switch_mlp.gate_proj", | |
| "model.layers.37.mlp.switch_mlp.up_proj", | |
| "model.layers.37.self_attn.g_proj", | |
| "model.layers.37.self_attn.k_proj", | |
| "model.layers.37.self_attn.o_proj", | |
| "model.layers.37.self_attn.q_proj", | |
| "model.layers.37.self_attn.v_proj", | |
| "model.layers.38.mlp.shared_expert.down_proj", | |
| "model.layers.38.mlp.shared_expert.gate_proj", | |
| "model.layers.38.mlp.shared_expert.up_proj", | |
| "model.layers.38.mlp.switch_mlp.down_proj", | |
| "model.layers.38.mlp.switch_mlp.gate_proj", | |
| "model.layers.38.mlp.switch_mlp.up_proj", | |
| "model.layers.38.self_attn.g_proj", | |
| "model.layers.38.self_attn.k_proj", | |
| "model.layers.38.self_attn.o_proj", | |
| "model.layers.38.self_attn.q_proj", | |
| "model.layers.38.self_attn.v_proj", | |
| "model.layers.39.mlp.shared_expert.down_proj", | |
| "model.layers.39.mlp.shared_expert.gate_proj", | |
| "model.layers.39.mlp.shared_expert.up_proj", | |
| "model.layers.39.mlp.switch_mlp.down_proj", | |
| "model.layers.39.mlp.switch_mlp.gate_proj", | |
| "model.layers.39.mlp.switch_mlp.up_proj", | |
| "model.layers.39.self_attn.g_proj", | |
| "model.layers.39.self_attn.k_proj", | |
| "model.layers.39.self_attn.o_proj", | |
| "model.layers.39.self_attn.q_proj", | |
| "model.layers.39.self_attn.v_proj", | |
| "model.layers.4.mlp.shared_expert.down_proj", | |
| "model.layers.4.mlp.shared_expert.gate_proj", | |
| "model.layers.4.mlp.shared_expert.up_proj", | |
| "model.layers.4.mlp.switch_mlp.down_proj", | |
| "model.layers.4.mlp.switch_mlp.gate_proj", | |
| "model.layers.4.mlp.switch_mlp.up_proj", | |
| "model.layers.4.self_attn.g_proj", | |
| "model.layers.4.self_attn.k_proj", | |
| "model.layers.4.self_attn.o_proj", | |
| "model.layers.4.self_attn.q_proj", | |
| "model.layers.4.self_attn.v_proj", | |
| "model.layers.5.mlp.shared_expert.down_proj", | |
| "model.layers.5.mlp.shared_expert.gate_proj", | |
| "model.layers.5.mlp.shared_expert.up_proj", | |
| "model.layers.5.mlp.switch_mlp.down_proj", | |
| "model.layers.5.mlp.switch_mlp.gate_proj", | |
| "model.layers.5.mlp.switch_mlp.up_proj", | |
| "model.layers.5.self_attn.g_proj", | |
| "model.layers.5.self_attn.k_proj", | |
| "model.layers.5.self_attn.o_proj", | |
| "model.layers.5.self_attn.q_proj", | |
| "model.layers.5.self_attn.v_proj", | |
| "model.layers.6.mlp.shared_expert.down_proj", | |
| "model.layers.6.mlp.shared_expert.gate_proj", | |
| "model.layers.6.mlp.shared_expert.up_proj", | |
| "model.layers.6.mlp.switch_mlp.down_proj", | |
| "model.layers.6.mlp.switch_mlp.gate_proj", | |
| "model.layers.6.mlp.switch_mlp.up_proj", | |
| "model.layers.6.self_attn.g_proj", | |
| "model.layers.6.self_attn.k_proj", | |
| "model.layers.6.self_attn.o_proj", | |
| "model.layers.6.self_attn.q_proj", | |
| "model.layers.6.self_attn.v_proj", | |
| "model.layers.7.mlp.shared_expert.down_proj", | |
| "model.layers.7.mlp.shared_expert.gate_proj", | |
| "model.layers.7.mlp.shared_expert.up_proj", | |
| "model.layers.7.mlp.switch_mlp.down_proj", | |
| "model.layers.7.mlp.switch_mlp.gate_proj", | |
| "model.layers.7.mlp.switch_mlp.up_proj", | |
| "model.layers.7.self_attn.g_proj", | |
| "model.layers.7.self_attn.k_proj", | |
| "model.layers.7.self_attn.o_proj", | |
| "model.layers.7.self_attn.q_proj", | |
| "model.layers.7.self_attn.v_proj", | |
| "model.layers.8.mlp.shared_expert.down_proj", | |
| "model.layers.8.mlp.shared_expert.gate_proj", | |
| "model.layers.8.mlp.shared_expert.up_proj", | |
| "model.layers.8.mlp.switch_mlp.down_proj", | |
| "model.layers.8.mlp.switch_mlp.gate_proj", | |
| "model.layers.8.mlp.switch_mlp.up_proj", | |
| "model.layers.8.self_attn.g_proj", | |
| "model.layers.8.self_attn.k_proj", | |
| "model.layers.8.self_attn.o_proj", | |
| "model.layers.8.self_attn.q_proj", | |
| "model.layers.8.self_attn.v_proj", | |
| "model.layers.9.mlp.shared_expert.down_proj", | |
| "model.layers.9.mlp.shared_expert.gate_proj", | |
| "model.layers.9.mlp.shared_expert.up_proj", | |
| "model.layers.9.mlp.switch_mlp.down_proj", | |
| "model.layers.9.mlp.switch_mlp.gate_proj", | |
| "model.layers.9.mlp.switch_mlp.up_proj", | |
| "model.layers.9.self_attn.g_proj", | |
| "model.layers.9.self_attn.k_proj", | |
| "model.layers.9.self_attn.o_proj", | |
| "model.layers.9.self_attn.q_proj", | |
| "model.layers.9.self_attn.v_proj" | |
| ], | |
| "missing": [ | |
| "lm_head", | |
| "model.embed_tokens" | |
| ], | |
| "mismatched": [], | |
| "zero_count_experts": 0 | |
| } |