MLX
Safetensors
qwen3_5_moe
oq
quantized
benchmark
performance
Mixture of Experts
code
agentic-coding
2-bit
Instructions to use mlx-works/KAT-Coder-V2.5-Dev-oQ2e with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-works/KAT-Coder-V2.5-Dev-oQ2e with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir KAT-Coder-V2.5-Dev-oQ2e mlx-works/KAT-Coder-V2.5-Dev-oQ2e
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "enabled": true, | |
| "cache_path": "/Users/jasen/.omlx/models/Kwaipilot/.oqe_imatrix/KAT-Coder-V2.5-Dev-oQe-s128-l512.npz", | |
| "cache_reused": true, | |
| "entry_count": 510, | |
| "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": 3, | |
| "micro_batches": 43, | |
| "batch_plan": { | |
| "micro_batch_size": 3, | |
| "estimated_sample_bytes": 33554432, | |
| "capture_budget_bytes": 115974430, | |
| "system_available_bytes": 26962821120, | |
| "metal_available_bytes": 26796267916, | |
| "live_available_bytes": 26796267916, | |
| "model_bytes": 15198824865, | |
| "remaining_available_bytes": 11597443051, | |
| "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": 128, | |
| "installed_modules": 511, | |
| "capture_module_classes": { | |
| "Linear": 40, | |
| "QuantizedLinear": 351, | |
| "QuantizedSwitchLinear": 120 | |
| }, | |
| "switch_capture_modules": 120, | |
| "requires_expert_counts": true, | |
| "coverage_sufficient": true, | |
| "collection_sufficient": true, | |
| "coverage": { | |
| "has_expert_counts": true, | |
| "expert_modules": 120, | |
| "total_experts": 30720, | |
| "active_experts": 30720, | |
| "zero_count_experts": 0, | |
| "active_ratio": 1.0, | |
| "min_count": 4, | |
| "p05_count": 548.0, | |
| "p10_count": 717.0, | |
| "median_count": 1762.0, | |
| "max_count": 18057, | |
| "min_required_count": 16, | |
| "required_percentile": 5 | |
| }, | |
| "rounds": [ | |
| { | |
| "processed_samples": 128, | |
| "coverage_sufficient": true, | |
| "collection_sufficient": true, | |
| "coverage": { | |
| "has_expert_counts": true, | |
| "expert_modules": 120, | |
| "total_experts": 30720, | |
| "active_experts": 30720, | |
| "zero_count_experts": 0, | |
| "active_ratio": 1.0, | |
| "min_count": 4, | |
| "p05_count": 548.0, | |
| "p10_count": 717.0, | |
| "median_count": 1762.0, | |
| "max_count": 18057, | |
| "min_required_count": 16, | |
| "required_percentile": 5 | |
| } | |
| } | |
| ] | |
| }, | |
| "expert_coverage": { | |
| "has_expert_counts": true, | |
| "expert_modules": 120, | |
| "total_experts": 30720, | |
| "active_experts": 30720, | |
| "zero_count_experts": 0, | |
| "active_ratio": 1.0, | |
| "min_count": 4, | |
| "p05_count": 548.0, | |
| "p10_count": 717.0, | |
| "median_count": 1762.0, | |
| "max_count": 18057, | |
| "min_required_count": 16, | |
| "required_percentile": 5 | |
| }, | |
| "applied": [ | |
| "language_model.model.layers.0.linear_attn.in_proj_a", | |
| "language_model.model.layers.0.linear_attn.in_proj_b", | |
| "language_model.model.layers.0.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.0.linear_attn.in_proj_z", | |
| "language_model.model.layers.0.linear_attn.out_proj", | |
| "language_model.model.layers.0.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.0.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.0.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.0.mlp.shared_expert_gate", | |
| "language_model.model.layers.0.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.0.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.0.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.1.linear_attn.in_proj_a", | |
| "language_model.model.layers.1.linear_attn.in_proj_b", | |
| "language_model.model.layers.1.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.1.linear_attn.in_proj_z", | |
| "language_model.model.layers.1.linear_attn.out_proj", | |
| "language_model.model.layers.1.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.1.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.1.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.1.mlp.shared_expert_gate", | |
| "language_model.model.layers.1.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.1.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.1.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.10.linear_attn.in_proj_a", | |
| "language_model.model.layers.10.linear_attn.in_proj_b", | |
| "language_model.model.layers.10.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.10.linear_attn.in_proj_z", | |
| "language_model.model.layers.10.linear_attn.out_proj", | |
| "language_model.model.layers.10.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.10.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.10.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.10.mlp.shared_expert_gate", | |
| "language_model.model.layers.10.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.10.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.10.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.11.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.11.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.11.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.11.mlp.shared_expert_gate", | |
| "language_model.model.layers.11.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.11.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.11.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.11.self_attn.k_proj", | |
| "language_model.model.layers.11.self_attn.o_proj", | |
| "language_model.model.layers.11.self_attn.q_proj", | |
| "language_model.model.layers.11.self_attn.v_proj", | |
| "language_model.model.layers.12.linear_attn.in_proj_a", | |
| "language_model.model.layers.12.linear_attn.in_proj_b", | |
| "language_model.model.layers.12.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.12.linear_attn.in_proj_z", | |
| "language_model.model.layers.12.linear_attn.out_proj", | |
| "language_model.model.layers.12.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.12.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.12.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.12.mlp.shared_expert_gate", | |
| "language_model.model.layers.12.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.12.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.12.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.13.linear_attn.in_proj_a", | |
| "language_model.model.layers.13.linear_attn.in_proj_b", | |
| "language_model.model.layers.13.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.13.linear_attn.in_proj_z", | |
| "language_model.model.layers.13.linear_attn.out_proj", | |
| "language_model.model.layers.13.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.13.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.13.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.13.mlp.shared_expert_gate", | |
| "language_model.model.layers.13.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.13.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.13.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.14.linear_attn.in_proj_a", | |
| "language_model.model.layers.14.linear_attn.in_proj_b", | |
| "language_model.model.layers.14.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.14.linear_attn.in_proj_z", | |
| "language_model.model.layers.14.linear_attn.out_proj", | |
| "language_model.model.layers.14.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.14.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.14.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.14.mlp.shared_expert_gate", | |
| "language_model.model.layers.14.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.14.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.14.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.15.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.15.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.15.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.15.mlp.shared_expert_gate", | |
| "language_model.model.layers.15.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.15.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.15.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.15.self_attn.k_proj", | |
| "language_model.model.layers.15.self_attn.o_proj", | |
| "language_model.model.layers.15.self_attn.q_proj", | |
| "language_model.model.layers.15.self_attn.v_proj", | |
| "language_model.model.layers.16.linear_attn.in_proj_a", | |
| "language_model.model.layers.16.linear_attn.in_proj_b", | |
| "language_model.model.layers.16.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.16.linear_attn.in_proj_z", | |
| "language_model.model.layers.16.linear_attn.out_proj", | |
| "language_model.model.layers.16.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.16.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.16.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.16.mlp.shared_expert_gate", | |
| "language_model.model.layers.16.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.16.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.16.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.17.linear_attn.in_proj_a", | |
| "language_model.model.layers.17.linear_attn.in_proj_b", | |
| "language_model.model.layers.17.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.17.linear_attn.in_proj_z", | |
| "language_model.model.layers.17.linear_attn.out_proj", | |
| "language_model.model.layers.17.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.17.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.17.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.17.mlp.shared_expert_gate", | |
| "language_model.model.layers.17.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.17.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.17.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.18.linear_attn.in_proj_a", | |
| "language_model.model.layers.18.linear_attn.in_proj_b", | |
| "language_model.model.layers.18.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.18.linear_attn.in_proj_z", | |
| "language_model.model.layers.18.linear_attn.out_proj", | |
| "language_model.model.layers.18.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.18.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.18.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.18.mlp.shared_expert_gate", | |
| "language_model.model.layers.18.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.18.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.18.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.19.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.19.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.19.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.19.mlp.shared_expert_gate", | |
| "language_model.model.layers.19.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.19.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.19.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.19.self_attn.k_proj", | |
| "language_model.model.layers.19.self_attn.o_proj", | |
| "language_model.model.layers.19.self_attn.q_proj", | |
| "language_model.model.layers.19.self_attn.v_proj", | |
| "language_model.model.layers.2.linear_attn.in_proj_a", | |
| "language_model.model.layers.2.linear_attn.in_proj_b", | |
| "language_model.model.layers.2.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.2.linear_attn.in_proj_z", | |
| "language_model.model.layers.2.linear_attn.out_proj", | |
| "language_model.model.layers.2.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.2.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.2.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.2.mlp.shared_expert_gate", | |
| "language_model.model.layers.2.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.2.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.2.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.20.linear_attn.in_proj_a", | |
| "language_model.model.layers.20.linear_attn.in_proj_b", | |
| "language_model.model.layers.20.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.20.linear_attn.in_proj_z", | |
| "language_model.model.layers.20.linear_attn.out_proj", | |
| "language_model.model.layers.20.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.20.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.20.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.20.mlp.shared_expert_gate", | |
| "language_model.model.layers.20.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.20.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.20.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.21.linear_attn.in_proj_a", | |
| "language_model.model.layers.21.linear_attn.in_proj_b", | |
| "language_model.model.layers.21.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.21.linear_attn.in_proj_z", | |
| "language_model.model.layers.21.linear_attn.out_proj", | |
| "language_model.model.layers.21.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.21.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.21.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.21.mlp.shared_expert_gate", | |
| "language_model.model.layers.21.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.21.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.21.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.22.linear_attn.in_proj_a", | |
| "language_model.model.layers.22.linear_attn.in_proj_b", | |
| "language_model.model.layers.22.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.22.linear_attn.in_proj_z", | |
| "language_model.model.layers.22.linear_attn.out_proj", | |
| "language_model.model.layers.22.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.22.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.22.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.22.mlp.shared_expert_gate", | |
| "language_model.model.layers.22.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.22.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.22.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.23.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.23.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.23.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.23.mlp.shared_expert_gate", | |
| "language_model.model.layers.23.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.23.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.23.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.23.self_attn.k_proj", | |
| "language_model.model.layers.23.self_attn.o_proj", | |
| "language_model.model.layers.23.self_attn.q_proj", | |
| "language_model.model.layers.23.self_attn.v_proj", | |
| "language_model.model.layers.24.linear_attn.in_proj_a", | |
| "language_model.model.layers.24.linear_attn.in_proj_b", | |
| "language_model.model.layers.24.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.24.linear_attn.in_proj_z", | |
| "language_model.model.layers.24.linear_attn.out_proj", | |
| "language_model.model.layers.24.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.24.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.24.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.24.mlp.shared_expert_gate", | |
| "language_model.model.layers.24.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.24.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.24.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.25.linear_attn.in_proj_a", | |
| "language_model.model.layers.25.linear_attn.in_proj_b", | |
| "language_model.model.layers.25.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.25.linear_attn.in_proj_z", | |
| "language_model.model.layers.25.linear_attn.out_proj", | |
| "language_model.model.layers.25.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.25.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.25.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.25.mlp.shared_expert_gate", | |
| "language_model.model.layers.25.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.25.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.25.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.26.linear_attn.in_proj_a", | |
| "language_model.model.layers.26.linear_attn.in_proj_b", | |
| "language_model.model.layers.26.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.26.linear_attn.in_proj_z", | |
| "language_model.model.layers.26.linear_attn.out_proj", | |
| "language_model.model.layers.26.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.26.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.26.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.26.mlp.shared_expert_gate", | |
| "language_model.model.layers.26.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.26.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.26.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.27.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.27.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.27.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.27.mlp.shared_expert_gate", | |
| "language_model.model.layers.27.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.27.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.27.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.27.self_attn.k_proj", | |
| "language_model.model.layers.27.self_attn.o_proj", | |
| "language_model.model.layers.27.self_attn.q_proj", | |
| "language_model.model.layers.27.self_attn.v_proj", | |
| "language_model.model.layers.28.linear_attn.in_proj_a", | |
| "language_model.model.layers.28.linear_attn.in_proj_b", | |
| "language_model.model.layers.28.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.28.linear_attn.in_proj_z", | |
| "language_model.model.layers.28.linear_attn.out_proj", | |
| "language_model.model.layers.28.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.28.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.28.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.28.mlp.shared_expert_gate", | |
| "language_model.model.layers.28.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.28.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.28.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.29.linear_attn.in_proj_a", | |
| "language_model.model.layers.29.linear_attn.in_proj_b", | |
| "language_model.model.layers.29.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.29.linear_attn.in_proj_z", | |
| "language_model.model.layers.29.linear_attn.out_proj", | |
| "language_model.model.layers.29.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.29.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.29.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.29.mlp.shared_expert_gate", | |
| "language_model.model.layers.29.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.29.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.29.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.3.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.3.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.3.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.3.mlp.shared_expert_gate", | |
| "language_model.model.layers.3.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.3.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.3.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.3.self_attn.k_proj", | |
| "language_model.model.layers.3.self_attn.o_proj", | |
| "language_model.model.layers.3.self_attn.q_proj", | |
| "language_model.model.layers.3.self_attn.v_proj", | |
| "language_model.model.layers.30.linear_attn.in_proj_a", | |
| "language_model.model.layers.30.linear_attn.in_proj_b", | |
| "language_model.model.layers.30.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.30.linear_attn.in_proj_z", | |
| "language_model.model.layers.30.linear_attn.out_proj", | |
| "language_model.model.layers.30.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.30.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.30.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.30.mlp.shared_expert_gate", | |
| "language_model.model.layers.30.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.30.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.30.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.31.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.31.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.31.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.31.mlp.shared_expert_gate", | |
| "language_model.model.layers.31.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.31.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.31.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.31.self_attn.k_proj", | |
| "language_model.model.layers.31.self_attn.o_proj", | |
| "language_model.model.layers.31.self_attn.q_proj", | |
| "language_model.model.layers.31.self_attn.v_proj", | |
| "language_model.model.layers.32.linear_attn.in_proj_a", | |
| "language_model.model.layers.32.linear_attn.in_proj_b", | |
| "language_model.model.layers.32.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.32.linear_attn.in_proj_z", | |
| "language_model.model.layers.32.linear_attn.out_proj", | |
| "language_model.model.layers.32.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.32.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.32.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.32.mlp.shared_expert_gate", | |
| "language_model.model.layers.32.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.32.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.32.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.33.linear_attn.in_proj_a", | |
| "language_model.model.layers.33.linear_attn.in_proj_b", | |
| "language_model.model.layers.33.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.33.linear_attn.in_proj_z", | |
| "language_model.model.layers.33.linear_attn.out_proj", | |
| "language_model.model.layers.33.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.33.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.33.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.33.mlp.shared_expert_gate", | |
| "language_model.model.layers.33.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.33.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.33.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.34.linear_attn.in_proj_a", | |
| "language_model.model.layers.34.linear_attn.in_proj_b", | |
| "language_model.model.layers.34.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.34.linear_attn.in_proj_z", | |
| "language_model.model.layers.34.linear_attn.out_proj", | |
| "language_model.model.layers.34.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.34.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.34.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.34.mlp.shared_expert_gate", | |
| "language_model.model.layers.34.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.34.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.34.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.35.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.35.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.35.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.35.mlp.shared_expert_gate", | |
| "language_model.model.layers.35.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.35.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.35.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.35.self_attn.k_proj", | |
| "language_model.model.layers.35.self_attn.o_proj", | |
| "language_model.model.layers.35.self_attn.q_proj", | |
| "language_model.model.layers.35.self_attn.v_proj", | |
| "language_model.model.layers.36.linear_attn.in_proj_a", | |
| "language_model.model.layers.36.linear_attn.in_proj_b", | |
| "language_model.model.layers.36.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.36.linear_attn.in_proj_z", | |
| "language_model.model.layers.36.linear_attn.out_proj", | |
| "language_model.model.layers.36.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.36.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.36.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.36.mlp.shared_expert_gate", | |
| "language_model.model.layers.36.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.36.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.36.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.37.linear_attn.in_proj_a", | |
| "language_model.model.layers.37.linear_attn.in_proj_b", | |
| "language_model.model.layers.37.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.37.linear_attn.in_proj_z", | |
| "language_model.model.layers.37.linear_attn.out_proj", | |
| "language_model.model.layers.37.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.37.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.37.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.37.mlp.shared_expert_gate", | |
| "language_model.model.layers.37.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.37.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.37.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.38.linear_attn.in_proj_a", | |
| "language_model.model.layers.38.linear_attn.in_proj_b", | |
| "language_model.model.layers.38.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.38.linear_attn.in_proj_z", | |
| "language_model.model.layers.38.linear_attn.out_proj", | |
| "language_model.model.layers.38.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.38.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.38.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.38.mlp.shared_expert_gate", | |
| "language_model.model.layers.38.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.38.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.38.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.39.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.39.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.39.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.39.mlp.shared_expert_gate", | |
| "language_model.model.layers.39.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.39.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.39.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.39.self_attn.k_proj", | |
| "language_model.model.layers.39.self_attn.o_proj", | |
| "language_model.model.layers.39.self_attn.q_proj", | |
| "language_model.model.layers.39.self_attn.v_proj", | |
| "language_model.model.layers.4.linear_attn.in_proj_a", | |
| "language_model.model.layers.4.linear_attn.in_proj_b", | |
| "language_model.model.layers.4.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.4.linear_attn.in_proj_z", | |
| "language_model.model.layers.4.linear_attn.out_proj", | |
| "language_model.model.layers.4.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.4.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.4.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.4.mlp.shared_expert_gate", | |
| "language_model.model.layers.4.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.4.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.4.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.5.linear_attn.in_proj_a", | |
| "language_model.model.layers.5.linear_attn.in_proj_b", | |
| "language_model.model.layers.5.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.5.linear_attn.in_proj_z", | |
| "language_model.model.layers.5.linear_attn.out_proj", | |
| "language_model.model.layers.5.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.5.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.5.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.5.mlp.shared_expert_gate", | |
| "language_model.model.layers.5.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.5.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.5.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.6.linear_attn.in_proj_a", | |
| "language_model.model.layers.6.linear_attn.in_proj_b", | |
| "language_model.model.layers.6.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.6.linear_attn.in_proj_z", | |
| "language_model.model.layers.6.linear_attn.out_proj", | |
| "language_model.model.layers.6.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.6.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.6.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.6.mlp.shared_expert_gate", | |
| "language_model.model.layers.6.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.6.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.6.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.7.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.7.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.7.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.7.mlp.shared_expert_gate", | |
| "language_model.model.layers.7.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.7.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.7.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.7.self_attn.k_proj", | |
| "language_model.model.layers.7.self_attn.o_proj", | |
| "language_model.model.layers.7.self_attn.q_proj", | |
| "language_model.model.layers.7.self_attn.v_proj", | |
| "language_model.model.layers.8.linear_attn.in_proj_a", | |
| "language_model.model.layers.8.linear_attn.in_proj_b", | |
| "language_model.model.layers.8.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.8.linear_attn.in_proj_z", | |
| "language_model.model.layers.8.linear_attn.out_proj", | |
| "language_model.model.layers.8.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.8.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.8.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.8.mlp.shared_expert_gate", | |
| "language_model.model.layers.8.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.8.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.8.mlp.switch_mlp.up_proj", | |
| "language_model.model.layers.9.linear_attn.in_proj_a", | |
| "language_model.model.layers.9.linear_attn.in_proj_b", | |
| "language_model.model.layers.9.linear_attn.in_proj_qkv", | |
| "language_model.model.layers.9.linear_attn.in_proj_z", | |
| "language_model.model.layers.9.linear_attn.out_proj", | |
| "language_model.model.layers.9.mlp.shared_expert.down_proj", | |
| "language_model.model.layers.9.mlp.shared_expert.gate_proj", | |
| "language_model.model.layers.9.mlp.shared_expert.up_proj", | |
| "language_model.model.layers.9.mlp.shared_expert_gate", | |
| "language_model.model.layers.9.mlp.switch_mlp.down_proj", | |
| "language_model.model.layers.9.mlp.switch_mlp.gate_proj", | |
| "language_model.model.layers.9.mlp.switch_mlp.up_proj" | |
| ], | |
| "missing": [ | |
| "language_model.lm_head", | |
| "language_model.model.embed_tokens" | |
| ], | |
| "mismatched": [], | |
| "zero_count_experts": 0 | |
| } |