Text Generation
MLX
Safetensors
qwen4_exp
omlx
oq
quantized
apple-silicon
mixture-of-experts
4-bit precision
long-context
conversational
tool-calling
speculative-decoding
mtp
Instructions to use jedisct1/Qwen3.8-Flash-Next-oQ4e-MTP-128k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use jedisct1/Qwen3.8-Flash-Next-oQ4e-MTP-128k 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("jedisct1/Qwen3.8-Flash-Next-oQ4e-MTP-128k") 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 jedisct1/Qwen3.8-Flash-Next-oQ4e-MTP-128k with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "jedisct1/Qwen3.8-Flash-Next-oQ4e-MTP-128k"
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": "jedisct1/Qwen3.8-Flash-Next-oQ4e-MTP-128k" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use jedisct1/Qwen3.8-Flash-Next-oQ4e-MTP-128k with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "jedisct1/Qwen3.8-Flash-Next-oQ4e-MTP-128k"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "jedisct1/Qwen3.8-Flash-Next-oQ4e-MTP-128k" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jedisct1/Qwen3.8-Flash-Next-oQ4e-MTP-128k", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use jedisct1/Qwen3.8-Flash-Next-oQ4e-MTP-128k 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 "jedisct1/Qwen3.8-Flash-Next-oQ4e-MTP-128k"
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 jedisct1/Qwen3.8-Flash-Next-oQ4e-MTP-128k
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use jedisct1/Qwen3.8-Flash-Next-oQ4e-MTP-128k with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "jedisct1/Qwen3.8-Flash-Next-oQ4e-MTP-128k"
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 "jedisct1/Qwen3.8-Flash-Next-oQ4e-MTP-128k" \ --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": null, | |
| "cache_reused": true, | |
| "entry_count": 914, | |
| "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": 6, | |
| "micro_batches": 176, | |
| "batch_plan": { | |
| "micro_batch_size": 6, | |
| "estimated_sample_bytes": 52428800, | |
| "capture_budget_bytes": 362029891, | |
| "system_available_bytes": 103756529664, | |
| "metal_available_bytes": 115443233112, | |
| "live_available_bytes": 103756529664, | |
| "model_bytes": 67553540501, | |
| "remaining_available_bytes": 36202989163, | |
| "fits_one_sample": true, | |
| "hidden_size": 2560, | |
| "num_experts": 512, | |
| "top_k": 10, | |
| "gemma4_state_bytes": 0, | |
| "num_hidden_layers": 48, | |
| "num_kv_shared_layers": 0, | |
| "per_layer_input_size": 0 | |
| }, | |
| "processed_samples": 1024, | |
| "installed_modules": 917, | |
| "capture_module_classes": { | |
| "Linear": 388, | |
| "QuantizedLinear": 385, | |
| "QuantizedSwitchLinear": 144 | |
| }, | |
| "switch_capture_modules": 144, | |
| "requires_expert_counts": true, | |
| "coverage_sufficient": false, | |
| "collection_sufficient": false, | |
| "coverage": { | |
| "has_expert_counts": true, | |
| "expert_modules": 144, | |
| "total_experts": 73728, | |
| "active_experts": 73665, | |
| "zero_count_experts": 63, | |
| "active_ratio": 0.9991455078125, | |
| "min_count": 0, | |
| "p05_count": 717.0, | |
| "p10_count": 1432.0, | |
| "median_count": 7353.0, | |
| "max_count": 341355, | |
| "min_required_count": 16, | |
| "required_percentile": 5 | |
| }, | |
| "rounds": [ | |
| { | |
| "processed_samples": 128, | |
| "coverage_sufficient": false, | |
| "collection_sufficient": false, | |
| "coverage": { | |
| "has_expert_counts": true, | |
| "expert_modules": 144, | |
| "total_experts": 73728, | |
| "active_experts": 73530, | |
| "zero_count_experts": 198, | |
| "active_ratio": 0.997314453125, | |
| "min_count": 0, | |
| "p05_count": 71.0, | |
| "p10_count": 158.0, | |
| "median_count": 913.0, | |
| "max_count": 41723, | |
| "min_required_count": 16, | |
| "required_percentile": 5 | |
| } | |
| }, | |
| { | |
| "processed_samples": 256, | |
| "coverage_sufficient": false, | |
| "collection_sufficient": false, | |
| "coverage": { | |
| "has_expert_counts": true, | |
| "expert_modules": 144, | |
| "total_experts": 73728, | |
| "active_experts": 73587, | |
| "zero_count_experts": 141, | |
| "active_ratio": 0.9980875651041666, | |
| "min_count": 0, | |
| "p05_count": 174.0, | |
| "p10_count": 353.0, | |
| "median_count": 1830.0, | |
| "max_count": 83264, | |
| "min_required_count": 16, | |
| "required_percentile": 5 | |
| } | |
| }, | |
| { | |
| "processed_samples": 384, | |
| "coverage_sufficient": false, | |
| "collection_sufficient": false, | |
| "coverage": { | |
| "has_expert_counts": true, | |
| "expert_modules": 144, | |
| "total_experts": 73728, | |
| "active_experts": 73629, | |
| "zero_count_experts": 99, | |
| "active_ratio": 0.9986572265625, | |
| "min_count": 0, | |
| "p05_count": 285.35000000000036, | |
| "p10_count": 553.0, | |
| "median_count": 2755.0, | |
| "max_count": 124541, | |
| "min_required_count": 16, | |
| "required_percentile": 5 | |
| } | |
| }, | |
| { | |
| "processed_samples": 512, | |
| "coverage_sufficient": false, | |
| "collection_sufficient": false, | |
| "coverage": { | |
| "has_expert_counts": true, | |
| "expert_modules": 144, | |
| "total_experts": 73728, | |
| "active_experts": 73641, | |
| "zero_count_experts": 87, | |
| "active_ratio": 0.9988199869791666, | |
| "min_count": 0, | |
| "p05_count": 369.35000000000036, | |
| "p10_count": 737.0, | |
| "median_count": 3687.5, | |
| "max_count": 168254, | |
| "min_required_count": 16, | |
| "required_percentile": 5 | |
| } | |
| }, | |
| { | |
| "processed_samples": 640, | |
| "coverage_sufficient": false, | |
| "collection_sufficient": false, | |
| "coverage": { | |
| "has_expert_counts": true, | |
| "expert_modules": 144, | |
| "total_experts": 73728, | |
| "active_experts": 73653, | |
| "zero_count_experts": 75, | |
| "active_ratio": 0.9989827473958334, | |
| "min_count": 0, | |
| "p05_count": 453.35000000000036, | |
| "p10_count": 904.0, | |
| "median_count": 4619.0, | |
| "max_count": 213373, | |
| "min_required_count": 16, | |
| "required_percentile": 5 | |
| } | |
| }, | |
| { | |
| "processed_samples": 768, | |
| "coverage_sufficient": false, | |
| "collection_sufficient": false, | |
| "coverage": { | |
| "has_expert_counts": true, | |
| "expert_modules": 144, | |
| "total_experts": 73728, | |
| "active_experts": 73656, | |
| "zero_count_experts": 72, | |
| "active_ratio": 0.9990234375, | |
| "min_count": 0, | |
| "p05_count": 539.0, | |
| "p10_count": 1076.0, | |
| "median_count": 5501.5, | |
| "max_count": 255296, | |
| "min_required_count": 16, | |
| "required_percentile": 5 | |
| } | |
| }, | |
| { | |
| "processed_samples": 896, | |
| "coverage_sufficient": false, | |
| "collection_sufficient": false, | |
| "coverage": { | |
| "has_expert_counts": true, | |
| "expert_modules": 144, | |
| "total_experts": 73728, | |
| "active_experts": 73659, | |
| "zero_count_experts": 69, | |
| "active_ratio": 0.9990641276041666, | |
| "min_count": 0, | |
| "p05_count": 628.0, | |
| "p10_count": 1257.0, | |
| "median_count": 6420.0, | |
| "max_count": 298656, | |
| "min_required_count": 16, | |
| "required_percentile": 5 | |
| } | |
| }, | |
| { | |
| "processed_samples": 1024, | |
| "coverage_sufficient": false, | |
| "collection_sufficient": false, | |
| "coverage": { | |
| "has_expert_counts": true, | |
| "expert_modules": 144, | |
| "total_experts": 73728, | |
| "active_experts": 73665, | |
| "zero_count_experts": 63, | |
| "active_ratio": 0.9991455078125, | |
| "min_count": 0, | |
| "p05_count": 717.0, | |
| "p10_count": 1432.0, | |
| "median_count": 7353.0, | |
| "max_count": 341355, | |
| "min_required_count": 16, | |
| "required_percentile": 5 | |
| } | |
| } | |
| ] | |
| }, | |
| "expert_coverage": { | |
| "has_expert_counts": true, | |
| "expert_modules": 144, | |
| "total_experts": 73728, | |
| "active_experts": 73665, | |
| "zero_count_experts": 63, | |
| "active_ratio": 0.9991455078125, | |
| "min_count": 0, | |
| "p05_count": 717.0, | |
| "p10_count": 1432.0, | |
| "median_count": 7353.0, | |
| "max_count": 341355, | |
| "min_required_count": 16, | |
| "required_percentile": 5 | |
| }, | |
| "applied": [ | |
| "model.layers.0.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.0.linear_attn.in_proj_a", | |
| "model.layers.0.linear_attn.in_proj_b", | |
| "model.layers.0.linear_attn.in_proj_qkv", | |
| "model.layers.0.linear_attn.in_proj_z", | |
| "model.layers.0.linear_attn.out_proj", | |
| "model.layers.0.mlp.shared_expert.down_proj", | |
| "model.layers.0.mlp.shared_expert.gate_proj", | |
| "model.layers.0.mlp.shared_expert.up_proj", | |
| "model.layers.0.mlp.switch_mlp.down_proj", | |
| "model.layers.0.mlp.switch_mlp.gate_proj", | |
| "model.layers.0.mlp.switch_mlp.up_proj", | |
| "model.layers.0.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.1.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.1.linear_attn.in_proj_a", | |
| "model.layers.1.linear_attn.in_proj_b", | |
| "model.layers.1.linear_attn.in_proj_qkv", | |
| "model.layers.1.linear_attn.in_proj_z", | |
| "model.layers.1.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.1.ple.key_proj", | |
| "model.layers.1.ple.value_proj", | |
| "model.layers.10.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.10.linear_attn.in_proj_a", | |
| "model.layers.10.linear_attn.in_proj_b", | |
| "model.layers.10.linear_attn.in_proj_qkv", | |
| "model.layers.10.linear_attn.in_proj_z", | |
| "model.layers.10.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.11.attn_hyper_connection.input_mix_weight_down", | |
| "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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.11.self_attn.indexer.index_qk_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.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.12.linear_attn.in_proj_a", | |
| "model.layers.12.linear_attn.in_proj_b", | |
| "model.layers.12.linear_attn.in_proj_qkv", | |
| "model.layers.12.linear_attn.in_proj_z", | |
| "model.layers.12.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.13.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.13.linear_attn.in_proj_a", | |
| "model.layers.13.linear_attn.in_proj_b", | |
| "model.layers.13.linear_attn.in_proj_qkv", | |
| "model.layers.13.linear_attn.in_proj_z", | |
| "model.layers.13.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.14.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.14.linear_attn.in_proj_a", | |
| "model.layers.14.linear_attn.in_proj_b", | |
| "model.layers.14.linear_attn.in_proj_qkv", | |
| "model.layers.14.linear_attn.in_proj_z", | |
| "model.layers.14.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.15.attn_hyper_connection.input_mix_weight_down", | |
| "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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.15.self_attn.indexer.index_qk_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.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.16.linear_attn.in_proj_a", | |
| "model.layers.16.linear_attn.in_proj_b", | |
| "model.layers.16.linear_attn.in_proj_qkv", | |
| "model.layers.16.linear_attn.in_proj_z", | |
| "model.layers.16.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.17.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.17.linear_attn.in_proj_a", | |
| "model.layers.17.linear_attn.in_proj_b", | |
| "model.layers.17.linear_attn.in_proj_qkv", | |
| "model.layers.17.linear_attn.in_proj_z", | |
| "model.layers.17.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.18.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.18.linear_attn.in_proj_a", | |
| "model.layers.18.linear_attn.in_proj_b", | |
| "model.layers.18.linear_attn.in_proj_qkv", | |
| "model.layers.18.linear_attn.in_proj_z", | |
| "model.layers.18.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.19.attn_hyper_connection.input_mix_weight_down", | |
| "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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.19.self_attn.indexer.index_qk_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.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.2.linear_attn.in_proj_a", | |
| "model.layers.2.linear_attn.in_proj_b", | |
| "model.layers.2.linear_attn.in_proj_qkv", | |
| "model.layers.2.linear_attn.in_proj_z", | |
| "model.layers.2.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.20.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.20.linear_attn.in_proj_a", | |
| "model.layers.20.linear_attn.in_proj_b", | |
| "model.layers.20.linear_attn.in_proj_qkv", | |
| "model.layers.20.linear_attn.in_proj_z", | |
| "model.layers.20.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.21.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.21.linear_attn.in_proj_a", | |
| "model.layers.21.linear_attn.in_proj_b", | |
| "model.layers.21.linear_attn.in_proj_qkv", | |
| "model.layers.21.linear_attn.in_proj_z", | |
| "model.layers.21.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.22.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.22.linear_attn.in_proj_a", | |
| "model.layers.22.linear_attn.in_proj_b", | |
| "model.layers.22.linear_attn.in_proj_qkv", | |
| "model.layers.22.linear_attn.in_proj_z", | |
| "model.layers.22.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.23.attn_hyper_connection.input_mix_weight_down", | |
| "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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.23.self_attn.indexer.index_qk_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.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.24.linear_attn.in_proj_a", | |
| "model.layers.24.linear_attn.in_proj_b", | |
| "model.layers.24.linear_attn.in_proj_qkv", | |
| "model.layers.24.linear_attn.in_proj_z", | |
| "model.layers.24.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.25.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.25.linear_attn.in_proj_a", | |
| "model.layers.25.linear_attn.in_proj_b", | |
| "model.layers.25.linear_attn.in_proj_qkv", | |
| "model.layers.25.linear_attn.in_proj_z", | |
| "model.layers.25.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.26.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.26.linear_attn.in_proj_a", | |
| "model.layers.26.linear_attn.in_proj_b", | |
| "model.layers.26.linear_attn.in_proj_qkv", | |
| "model.layers.26.linear_attn.in_proj_z", | |
| "model.layers.26.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.27.attn_hyper_connection.input_mix_weight_down", | |
| "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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.27.self_attn.indexer.index_qk_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.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.28.linear_attn.in_proj_a", | |
| "model.layers.28.linear_attn.in_proj_b", | |
| "model.layers.28.linear_attn.in_proj_qkv", | |
| "model.layers.28.linear_attn.in_proj_z", | |
| "model.layers.28.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.29.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.29.linear_attn.in_proj_a", | |
| "model.layers.29.linear_attn.in_proj_b", | |
| "model.layers.29.linear_attn.in_proj_qkv", | |
| "model.layers.29.linear_attn.in_proj_z", | |
| "model.layers.29.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.3.attn_hyper_connection.input_mix_weight_down", | |
| "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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.3.self_attn.indexer.index_qk_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.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.30.linear_attn.in_proj_a", | |
| "model.layers.30.linear_attn.in_proj_b", | |
| "model.layers.30.linear_attn.in_proj_qkv", | |
| "model.layers.30.linear_attn.in_proj_z", | |
| "model.layers.30.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.31.attn_hyper_connection.input_mix_weight_down", | |
| "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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.31.self_attn.indexer.index_qk_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.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.32.linear_attn.in_proj_a", | |
| "model.layers.32.linear_attn.in_proj_b", | |
| "model.layers.32.linear_attn.in_proj_qkv", | |
| "model.layers.32.linear_attn.in_proj_z", | |
| "model.layers.32.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.33.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.33.linear_attn.in_proj_a", | |
| "model.layers.33.linear_attn.in_proj_b", | |
| "model.layers.33.linear_attn.in_proj_qkv", | |
| "model.layers.33.linear_attn.in_proj_z", | |
| "model.layers.33.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.34.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.34.linear_attn.in_proj_a", | |
| "model.layers.34.linear_attn.in_proj_b", | |
| "model.layers.34.linear_attn.in_proj_qkv", | |
| "model.layers.34.linear_attn.in_proj_z", | |
| "model.layers.34.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.35.attn_hyper_connection.input_mix_weight_down", | |
| "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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.35.self_attn.indexer.index_qk_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.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.36.linear_attn.in_proj_a", | |
| "model.layers.36.linear_attn.in_proj_b", | |
| "model.layers.36.linear_attn.in_proj_qkv", | |
| "model.layers.36.linear_attn.in_proj_z", | |
| "model.layers.36.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.37.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.37.linear_attn.in_proj_a", | |
| "model.layers.37.linear_attn.in_proj_b", | |
| "model.layers.37.linear_attn.in_proj_qkv", | |
| "model.layers.37.linear_attn.in_proj_z", | |
| "model.layers.37.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.38.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.38.linear_attn.in_proj_a", | |
| "model.layers.38.linear_attn.in_proj_b", | |
| "model.layers.38.linear_attn.in_proj_qkv", | |
| "model.layers.38.linear_attn.in_proj_z", | |
| "model.layers.38.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.39.attn_hyper_connection.input_mix_weight_down", | |
| "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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.39.self_attn.indexer.index_qk_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.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.4.linear_attn.in_proj_a", | |
| "model.layers.4.linear_attn.in_proj_b", | |
| "model.layers.4.linear_attn.in_proj_qkv", | |
| "model.layers.4.linear_attn.in_proj_z", | |
| "model.layers.4.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.40.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.40.linear_attn.in_proj_a", | |
| "model.layers.40.linear_attn.in_proj_b", | |
| "model.layers.40.linear_attn.in_proj_qkv", | |
| "model.layers.40.linear_attn.in_proj_z", | |
| "model.layers.40.linear_attn.out_proj", | |
| "model.layers.40.mlp.shared_expert.down_proj", | |
| "model.layers.40.mlp.shared_expert.gate_proj", | |
| "model.layers.40.mlp.shared_expert.up_proj", | |
| "model.layers.40.mlp.switch_mlp.down_proj", | |
| "model.layers.40.mlp.switch_mlp.gate_proj", | |
| "model.layers.40.mlp.switch_mlp.up_proj", | |
| "model.layers.40.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.41.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.41.linear_attn.in_proj_a", | |
| "model.layers.41.linear_attn.in_proj_b", | |
| "model.layers.41.linear_attn.in_proj_qkv", | |
| "model.layers.41.linear_attn.in_proj_z", | |
| "model.layers.41.linear_attn.out_proj", | |
| "model.layers.41.mlp.shared_expert.down_proj", | |
| "model.layers.41.mlp.shared_expert.gate_proj", | |
| "model.layers.41.mlp.shared_expert.up_proj", | |
| "model.layers.41.mlp.switch_mlp.down_proj", | |
| "model.layers.41.mlp.switch_mlp.gate_proj", | |
| "model.layers.41.mlp.switch_mlp.up_proj", | |
| "model.layers.41.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.42.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.42.linear_attn.in_proj_a", | |
| "model.layers.42.linear_attn.in_proj_b", | |
| "model.layers.42.linear_attn.in_proj_qkv", | |
| "model.layers.42.linear_attn.in_proj_z", | |
| "model.layers.42.linear_attn.out_proj", | |
| "model.layers.42.mlp.shared_expert.down_proj", | |
| "model.layers.42.mlp.shared_expert.gate_proj", | |
| "model.layers.42.mlp.shared_expert.up_proj", | |
| "model.layers.42.mlp.switch_mlp.down_proj", | |
| "model.layers.42.mlp.switch_mlp.gate_proj", | |
| "model.layers.42.mlp.switch_mlp.up_proj", | |
| "model.layers.42.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.43.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.43.mlp.shared_expert.down_proj", | |
| "model.layers.43.mlp.shared_expert.gate_proj", | |
| "model.layers.43.mlp.shared_expert.up_proj", | |
| "model.layers.43.mlp.switch_mlp.down_proj", | |
| "model.layers.43.mlp.switch_mlp.gate_proj", | |
| "model.layers.43.mlp.switch_mlp.up_proj", | |
| "model.layers.43.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.43.self_attn.indexer.index_qk_proj", | |
| "model.layers.43.self_attn.k_proj", | |
| "model.layers.43.self_attn.o_proj", | |
| "model.layers.43.self_attn.q_proj", | |
| "model.layers.43.self_attn.v_proj", | |
| "model.layers.44.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.44.linear_attn.in_proj_a", | |
| "model.layers.44.linear_attn.in_proj_b", | |
| "model.layers.44.linear_attn.in_proj_qkv", | |
| "model.layers.44.linear_attn.in_proj_z", | |
| "model.layers.44.linear_attn.out_proj", | |
| "model.layers.44.mlp.shared_expert.down_proj", | |
| "model.layers.44.mlp.shared_expert.gate_proj", | |
| "model.layers.44.mlp.shared_expert.up_proj", | |
| "model.layers.44.mlp.switch_mlp.down_proj", | |
| "model.layers.44.mlp.switch_mlp.gate_proj", | |
| "model.layers.44.mlp.switch_mlp.up_proj", | |
| "model.layers.44.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.45.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.45.linear_attn.in_proj_a", | |
| "model.layers.45.linear_attn.in_proj_b", | |
| "model.layers.45.linear_attn.in_proj_qkv", | |
| "model.layers.45.linear_attn.in_proj_z", | |
| "model.layers.45.linear_attn.out_proj", | |
| "model.layers.45.mlp.shared_expert.down_proj", | |
| "model.layers.45.mlp.shared_expert.gate_proj", | |
| "model.layers.45.mlp.shared_expert.up_proj", | |
| "model.layers.45.mlp.switch_mlp.down_proj", | |
| "model.layers.45.mlp.switch_mlp.gate_proj", | |
| "model.layers.45.mlp.switch_mlp.up_proj", | |
| "model.layers.45.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.46.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.46.linear_attn.in_proj_a", | |
| "model.layers.46.linear_attn.in_proj_b", | |
| "model.layers.46.linear_attn.in_proj_qkv", | |
| "model.layers.46.linear_attn.in_proj_z", | |
| "model.layers.46.linear_attn.out_proj", | |
| "model.layers.46.mlp.shared_expert.down_proj", | |
| "model.layers.46.mlp.shared_expert.gate_proj", | |
| "model.layers.46.mlp.shared_expert.up_proj", | |
| "model.layers.46.mlp.switch_mlp.down_proj", | |
| "model.layers.46.mlp.switch_mlp.gate_proj", | |
| "model.layers.46.mlp.switch_mlp.up_proj", | |
| "model.layers.46.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.47.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.47.mlp.shared_expert.down_proj", | |
| "model.layers.47.mlp.shared_expert.gate_proj", | |
| "model.layers.47.mlp.shared_expert.up_proj", | |
| "model.layers.47.mlp.switch_mlp.down_proj", | |
| "model.layers.47.mlp.switch_mlp.gate_proj", | |
| "model.layers.47.mlp.switch_mlp.up_proj", | |
| "model.layers.47.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.47.self_attn.indexer.index_qk_proj", | |
| "model.layers.47.self_attn.k_proj", | |
| "model.layers.47.self_attn.o_proj", | |
| "model.layers.47.self_attn.q_proj", | |
| "model.layers.47.self_attn.v_proj", | |
| "model.layers.5.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.5.linear_attn.in_proj_a", | |
| "model.layers.5.linear_attn.in_proj_b", | |
| "model.layers.5.linear_attn.in_proj_qkv", | |
| "model.layers.5.linear_attn.in_proj_z", | |
| "model.layers.5.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.6.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.6.linear_attn.in_proj_a", | |
| "model.layers.6.linear_attn.in_proj_b", | |
| "model.layers.6.linear_attn.in_proj_qkv", | |
| "model.layers.6.linear_attn.in_proj_z", | |
| "model.layers.6.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.7.attn_hyper_connection.input_mix_weight_down", | |
| "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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.7.self_attn.indexer.index_qk_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.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.8.linear_attn.in_proj_a", | |
| "model.layers.8.linear_attn.in_proj_b", | |
| "model.layers.8.linear_attn.in_proj_qkv", | |
| "model.layers.8.linear_attn.in_proj_z", | |
| "model.layers.8.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down", | |
| "model.layers.9.attn_hyper_connection.input_mix_weight_down", | |
| "model.layers.9.linear_attn.in_proj_a", | |
| "model.layers.9.linear_attn.in_proj_b", | |
| "model.layers.9.linear_attn.in_proj_qkv", | |
| "model.layers.9.linear_attn.in_proj_z", | |
| "model.layers.9.linear_attn.out_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.mlp_hyper_connection.input_mix_weight_down" | |
| ], | |
| "missing": [], | |
| "mismatched": [], | |
| "zero_count_experts": 63 | |
| } | |