|
{ |
|
"_name_or_path": "mistralai/Mixtral-8x22B-v0.1", |
|
"architectures": [ |
|
"MixtralForCausalLM" |
|
], |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 1, |
|
"eos_token_id": 2, |
|
"head_dim": 128, |
|
"hidden_act": "silu", |
|
"hidden_size": 6144, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 16384, |
|
"max_position_embeddings": 65536, |
|
"model_type": "mixtral", |
|
"num_attention_heads": 48, |
|
"num_experts_per_tok": 2, |
|
"num_hidden_layers": 56, |
|
"num_key_value_heads": 8, |
|
"num_local_experts": 8, |
|
"output_router_logits": false, |
|
"quantization_config": { |
|
"config_groups": { |
|
"group_0": { |
|
"input_activations": null, |
|
"output_activations": null, |
|
"targets": [ |
|
"Linear" |
|
], |
|
"weights": { |
|
"actorder": null, |
|
"block_structure": null, |
|
"dynamic": false, |
|
"group_size": null, |
|
"num_bits": 4, |
|
"observer": "minmax", |
|
"observer_kwargs": {}, |
|
"strategy": "channel", |
|
"symmetric": true, |
|
"type": "int" |
|
} |
|
} |
|
}, |
|
"format": "pack-quantized", |
|
"global_compression_ratio": 2.102105512128843, |
|
"ignore": [ |
|
"model.layers.0.block_sparse_moe.gate", |
|
"model.layers.1.block_sparse_moe.gate", |
|
"model.layers.2.block_sparse_moe.gate", |
|
"model.layers.3.block_sparse_moe.gate", |
|
"model.layers.4.block_sparse_moe.gate", |
|
"model.layers.5.block_sparse_moe.gate", |
|
"model.layers.6.block_sparse_moe.gate", |
|
"model.layers.7.block_sparse_moe.gate", |
|
"model.layers.8.block_sparse_moe.gate", |
|
"model.layers.9.block_sparse_moe.gate", |
|
"model.layers.10.block_sparse_moe.gate", |
|
"model.layers.11.block_sparse_moe.gate", |
|
"model.layers.12.block_sparse_moe.gate", |
|
"model.layers.13.block_sparse_moe.gate", |
|
"model.layers.14.block_sparse_moe.gate", |
|
"model.layers.15.block_sparse_moe.gate", |
|
"model.layers.16.block_sparse_moe.gate", |
|
"model.layers.17.block_sparse_moe.gate", |
|
"model.layers.18.block_sparse_moe.gate", |
|
"model.layers.19.block_sparse_moe.gate", |
|
"model.layers.20.block_sparse_moe.gate", |
|
"model.layers.21.block_sparse_moe.gate", |
|
"model.layers.22.block_sparse_moe.gate", |
|
"model.layers.23.block_sparse_moe.gate", |
|
"model.layers.24.block_sparse_moe.gate", |
|
"model.layers.25.block_sparse_moe.gate", |
|
"model.layers.26.block_sparse_moe.gate", |
|
"model.layers.27.block_sparse_moe.gate", |
|
"model.layers.28.block_sparse_moe.gate", |
|
"model.layers.29.block_sparse_moe.gate", |
|
"model.layers.30.block_sparse_moe.gate", |
|
"model.layers.31.block_sparse_moe.gate", |
|
"model.layers.32.block_sparse_moe.gate", |
|
"model.layers.33.block_sparse_moe.gate", |
|
"model.layers.34.block_sparse_moe.gate", |
|
"model.layers.35.block_sparse_moe.gate", |
|
"model.layers.36.block_sparse_moe.gate", |
|
"model.layers.37.block_sparse_moe.gate", |
|
"model.layers.38.block_sparse_moe.gate", |
|
"model.layers.39.block_sparse_moe.gate", |
|
"model.layers.40.block_sparse_moe.gate", |
|
"model.layers.41.block_sparse_moe.gate", |
|
"model.layers.42.block_sparse_moe.gate", |
|
"model.layers.43.block_sparse_moe.gate", |
|
"model.layers.44.block_sparse_moe.gate", |
|
"model.layers.45.block_sparse_moe.gate", |
|
"model.layers.46.block_sparse_moe.gate", |
|
"model.layers.47.block_sparse_moe.gate", |
|
"model.layers.48.block_sparse_moe.gate", |
|
"model.layers.49.block_sparse_moe.gate", |
|
"model.layers.50.block_sparse_moe.gate", |
|
"model.layers.51.block_sparse_moe.gate", |
|
"model.layers.52.block_sparse_moe.gate", |
|
"model.layers.53.block_sparse_moe.gate", |
|
"model.layers.54.block_sparse_moe.gate", |
|
"model.layers.55.block_sparse_moe.gate", |
|
"lm_head" |
|
], |
|
"kv_cache_scheme": null, |
|
"quant_method": "compressed-tensors", |
|
"quantization_status": "compressed", |
|
"sparsity_config": { |
|
"format": "dense", |
|
"global_sparsity": 0.21683202346977445, |
|
"ignore": [ |
|
"model.layers.0.self_attn.o_proj", |
|
"model.layers.0.block_sparse_moe.gate", |
|
"model.layers.0.block_sparse_moe.experts.0.w1", |
|
"model.layers.0.block_sparse_moe.experts.0.w2", |
|
"model.layers.0.block_sparse_moe.experts.0.w3", |
|
"model.layers.0.block_sparse_moe.experts.1.w1", |
|
"model.layers.0.block_sparse_moe.experts.1.w2", |
|
"model.layers.0.block_sparse_moe.experts.1.w3", |
|
"model.layers.0.block_sparse_moe.experts.2.w1", |
|
"model.layers.0.block_sparse_moe.experts.2.w2", |
|
"model.layers.0.block_sparse_moe.experts.2.w3", |
|
"model.layers.0.block_sparse_moe.experts.3.w1", |
|
"model.layers.0.block_sparse_moe.experts.3.w2", |
|
"model.layers.0.block_sparse_moe.experts.3.w3", |
|
"model.layers.0.block_sparse_moe.experts.4.w1", |
|
"model.layers.0.block_sparse_moe.experts.4.w2", |
|
"model.layers.0.block_sparse_moe.experts.4.w3", |
|
"model.layers.0.block_sparse_moe.experts.5.w1", |
|
"model.layers.0.block_sparse_moe.experts.5.w2", |
|
"model.layers.0.block_sparse_moe.experts.5.w3", |
|
"model.layers.0.block_sparse_moe.experts.6.w1", |
|
"model.layers.0.block_sparse_moe.experts.6.w2", |
|
"model.layers.0.block_sparse_moe.experts.6.w3", |
|
"model.layers.0.block_sparse_moe.experts.7.w1", |
|
"model.layers.0.block_sparse_moe.experts.7.w2", |
|
"model.layers.0.block_sparse_moe.experts.7.w3", |
|
"model.layers.1.self_attn.v_proj", |
|
"model.layers.1.self_attn.o_proj", |
|
"model.layers.1.block_sparse_moe.gate", |
|
"model.layers.1.block_sparse_moe.experts.0.w1", |
|
"model.layers.1.block_sparse_moe.experts.0.w2", |
|
"model.layers.1.block_sparse_moe.experts.0.w3", |
|
"model.layers.1.block_sparse_moe.experts.1.w1", |
|
"model.layers.1.block_sparse_moe.experts.1.w2", |
|
"model.layers.1.block_sparse_moe.experts.1.w3", |
|
"model.layers.1.block_sparse_moe.experts.2.w1", |
|
"model.layers.1.block_sparse_moe.experts.2.w2", |
|
"model.layers.1.block_sparse_moe.experts.2.w3", |
|
"model.layers.1.block_sparse_moe.experts.3.w1", |
|
"model.layers.1.block_sparse_moe.experts.3.w2", |
|
"model.layers.1.block_sparse_moe.experts.3.w3", |
|
"model.layers.1.block_sparse_moe.experts.4.w1", |
|
"model.layers.1.block_sparse_moe.experts.4.w2", |
|
"model.layers.1.block_sparse_moe.experts.4.w3", |
|
"model.layers.1.block_sparse_moe.experts.5.w1", |
|
"model.layers.1.block_sparse_moe.experts.5.w2", |
|
"model.layers.1.block_sparse_moe.experts.5.w3", |
|
"model.layers.1.block_sparse_moe.experts.6.w1", |
|
"model.layers.1.block_sparse_moe.experts.6.w2", |
|
"model.layers.1.block_sparse_moe.experts.6.w3", |
|
"model.layers.1.block_sparse_moe.experts.7.w1", |
|
"model.layers.1.block_sparse_moe.experts.7.w2", |
|
"model.layers.1.block_sparse_moe.experts.7.w3", |
|
"model.layers.2.self_attn.q_proj", |
|
"model.layers.2.self_attn.k_proj", |
|
"model.layers.2.self_attn.v_proj", |
|
"model.layers.2.self_attn.o_proj", |
|
"model.layers.2.block_sparse_moe.gate", |
|
"model.layers.2.block_sparse_moe.experts.0.w1", |
|
"model.layers.2.block_sparse_moe.experts.0.w2", |
|
"model.layers.2.block_sparse_moe.experts.0.w3", |
|
"model.layers.2.block_sparse_moe.experts.1.w1", |
|
"model.layers.2.block_sparse_moe.experts.1.w2", |
|
"model.layers.2.block_sparse_moe.experts.1.w3", |
|
"model.layers.2.block_sparse_moe.experts.2.w1", |
|
"model.layers.2.block_sparse_moe.experts.2.w2", |
|
"model.layers.2.block_sparse_moe.experts.2.w3", |
|
"model.layers.2.block_sparse_moe.experts.3.w1", |
|
"model.layers.2.block_sparse_moe.experts.3.w2", |
|
"model.layers.2.block_sparse_moe.experts.3.w3", |
|
"model.layers.2.block_sparse_moe.experts.4.w1", |
|
"model.layers.2.block_sparse_moe.experts.4.w2", |
|
"model.layers.2.block_sparse_moe.experts.4.w3", |
|
"model.layers.2.block_sparse_moe.experts.5.w1", |
|
"model.layers.2.block_sparse_moe.experts.5.w2", |
|
"model.layers.2.block_sparse_moe.experts.5.w3", |
|
"model.layers.2.block_sparse_moe.experts.6.w1", |
|
"model.layers.2.block_sparse_moe.experts.6.w2", |
|
"model.layers.2.block_sparse_moe.experts.6.w3", |
|
"model.layers.2.block_sparse_moe.experts.7.w1", |
|
"model.layers.2.block_sparse_moe.experts.7.w2", |
|
"model.layers.2.block_sparse_moe.experts.7.w3", |
|
"model.layers.3.self_attn.q_proj", |
|
"model.layers.3.self_attn.k_proj", |
|
"model.layers.3.self_attn.v_proj", |
|
"model.layers.3.self_attn.o_proj", |
|
"model.layers.3.block_sparse_moe.gate", |
|
"model.layers.3.block_sparse_moe.experts.0.w1", |
|
"model.layers.3.block_sparse_moe.experts.0.w2", |
|
"model.layers.3.block_sparse_moe.experts.0.w3", |
|
"model.layers.3.block_sparse_moe.experts.1.w1", |
|
"model.layers.3.block_sparse_moe.experts.1.w2", |
|
"model.layers.3.block_sparse_moe.experts.1.w3", |
|
"model.layers.3.block_sparse_moe.experts.2.w1", |
|
"model.layers.3.block_sparse_moe.experts.2.w2", |
|
"model.layers.3.block_sparse_moe.experts.2.w3", |
|
"model.layers.3.block_sparse_moe.experts.3.w1", |
|
"model.layers.3.block_sparse_moe.experts.3.w2", |
|
"model.layers.3.block_sparse_moe.experts.3.w3", |
|
"model.layers.3.block_sparse_moe.experts.4.w1", |
|
"model.layers.3.block_sparse_moe.experts.4.w2", |
|
"model.layers.3.block_sparse_moe.experts.4.w3", |
|
"model.layers.3.block_sparse_moe.experts.5.w1", |
|
"model.layers.3.block_sparse_moe.experts.5.w2", |
|
"model.layers.3.block_sparse_moe.experts.5.w3", |
|
"model.layers.3.block_sparse_moe.experts.6.w1", |
|
"model.layers.3.block_sparse_moe.experts.6.w2", |
|
"model.layers.3.block_sparse_moe.experts.6.w3", |
|
"model.layers.3.block_sparse_moe.experts.7.w1", |
|
"model.layers.3.block_sparse_moe.experts.7.w2", |
|
"model.layers.3.block_sparse_moe.experts.7.w3", |
|
"model.layers.4.self_attn.q_proj", |
|
"model.layers.4.self_attn.k_proj", |
|
"model.layers.4.self_attn.v_proj", |
|
"model.layers.4.self_attn.o_proj", |
|
"model.layers.4.block_sparse_moe.gate", |
|
"model.layers.4.block_sparse_moe.experts.0.w1", |
|
"model.layers.4.block_sparse_moe.experts.0.w2", |
|
"model.layers.4.block_sparse_moe.experts.0.w3", |
|
"model.layers.4.block_sparse_moe.experts.1.w1", |
|
"model.layers.4.block_sparse_moe.experts.1.w2", |
|
"model.layers.4.block_sparse_moe.experts.1.w3", |
|
"model.layers.4.block_sparse_moe.experts.2.w1", |
|
"model.layers.4.block_sparse_moe.experts.2.w2", |
|
"model.layers.4.block_sparse_moe.experts.2.w3", |
|
"model.layers.4.block_sparse_moe.experts.3.w1", |
|
"model.layers.4.block_sparse_moe.experts.3.w2", |
|
"model.layers.4.block_sparse_moe.experts.3.w3", |
|
"model.layers.4.block_sparse_moe.experts.4.w1", |
|
"model.layers.4.block_sparse_moe.experts.4.w2", |
|
"model.layers.4.block_sparse_moe.experts.4.w3", |
|
"model.layers.4.block_sparse_moe.experts.5.w1", |
|
"model.layers.4.block_sparse_moe.experts.5.w2", |
|
"model.layers.4.block_sparse_moe.experts.5.w3", |
|
"model.layers.4.block_sparse_moe.experts.6.w1", |
|
"model.layers.4.block_sparse_moe.experts.6.w2", |
|
"model.layers.4.block_sparse_moe.experts.6.w3", |
|
"model.layers.4.block_sparse_moe.experts.7.w1", |
|
"model.layers.4.block_sparse_moe.experts.7.w2", |
|
"model.layers.4.block_sparse_moe.experts.7.w3", |
|
"model.layers.5.self_attn.q_proj", |
|
"model.layers.5.self_attn.k_proj", |
|
"model.layers.5.self_attn.v_proj", |
|
"model.layers.5.self_attn.o_proj", |
|
"model.layers.5.block_sparse_moe.gate", |
|
"model.layers.5.block_sparse_moe.experts.0.w1", |
|
"model.layers.5.block_sparse_moe.experts.0.w2", |
|
"model.layers.5.block_sparse_moe.experts.0.w3", |
|
"model.layers.5.block_sparse_moe.experts.1.w1", |
|
"model.layers.5.block_sparse_moe.experts.1.w2", |
|
"model.layers.5.block_sparse_moe.experts.1.w3", |
|
"model.layers.5.block_sparse_moe.experts.2.w1", |
|
"model.layers.5.block_sparse_moe.experts.2.w2", |
|
"model.layers.5.block_sparse_moe.experts.2.w3", |
|
"model.layers.5.block_sparse_moe.experts.3.w1", |
|
"model.layers.5.block_sparse_moe.experts.3.w2", |
|
"model.layers.5.block_sparse_moe.experts.3.w3", |
|
"model.layers.5.block_sparse_moe.experts.4.w1", |
|
"model.layers.5.block_sparse_moe.experts.4.w2", |
|
"model.layers.5.block_sparse_moe.experts.4.w3", |
|
"model.layers.5.block_sparse_moe.experts.5.w1", |
|
"model.layers.5.block_sparse_moe.experts.5.w2", |
|
"model.layers.5.block_sparse_moe.experts.5.w3", |
|
"model.layers.5.block_sparse_moe.experts.6.w1", |
|
"model.layers.5.block_sparse_moe.experts.6.w2", |
|
"model.layers.5.block_sparse_moe.experts.6.w3", |
|
"model.layers.5.block_sparse_moe.experts.7.w1", |
|
"model.layers.5.block_sparse_moe.experts.7.w2", |
|
"model.layers.5.block_sparse_moe.experts.7.w3", |
|
"model.layers.6.self_attn.q_proj", |
|
"model.layers.6.self_attn.k_proj", |
|
"model.layers.6.self_attn.v_proj", |
|
"model.layers.6.self_attn.o_proj", |
|
"model.layers.6.block_sparse_moe.gate", |
|
"model.layers.6.block_sparse_moe.experts.0.w1", |
|
"model.layers.6.block_sparse_moe.experts.0.w2", |
|
"model.layers.6.block_sparse_moe.experts.0.w3", |
|
"model.layers.6.block_sparse_moe.experts.1.w1", |
|
"model.layers.6.block_sparse_moe.experts.1.w2", |
|
"model.layers.6.block_sparse_moe.experts.1.w3", |
|
"model.layers.6.block_sparse_moe.experts.2.w1", |
|
"model.layers.6.block_sparse_moe.experts.2.w2", |
|
"model.layers.6.block_sparse_moe.experts.2.w3", |
|
"model.layers.6.block_sparse_moe.experts.3.w1", |
|
"model.layers.6.block_sparse_moe.experts.3.w2", |
|
"model.layers.6.block_sparse_moe.experts.3.w3", |
|
"model.layers.6.block_sparse_moe.experts.4.w1", |
|
"model.layers.6.block_sparse_moe.experts.4.w2", |
|
"model.layers.6.block_sparse_moe.experts.4.w3", |
|
"model.layers.6.block_sparse_moe.experts.5.w1", |
|
"model.layers.6.block_sparse_moe.experts.5.w2", |
|
"model.layers.6.block_sparse_moe.experts.5.w3", |
|
"model.layers.6.block_sparse_moe.experts.6.w1", |
|
"model.layers.6.block_sparse_moe.experts.6.w2", |
|
"model.layers.6.block_sparse_moe.experts.6.w3", |
|
"model.layers.6.block_sparse_moe.experts.7.w1", |
|
"model.layers.6.block_sparse_moe.experts.7.w2", |
|
"model.layers.6.block_sparse_moe.experts.7.w3", |
|
"model.layers.7.self_attn.q_proj", |
|
"model.layers.7.self_attn.k_proj", |
|
"model.layers.7.self_attn.v_proj", |
|
"model.layers.7.self_attn.o_proj", |
|
"model.layers.7.block_sparse_moe.gate", |
|
"model.layers.7.block_sparse_moe.experts.0.w1", |
|
"model.layers.7.block_sparse_moe.experts.0.w2", |
|
"model.layers.7.block_sparse_moe.experts.0.w3", |
|
"model.layers.7.block_sparse_moe.experts.1.w1", |
|
"model.layers.7.block_sparse_moe.experts.1.w2", |
|
"model.layers.7.block_sparse_moe.experts.1.w3", |
|
"model.layers.7.block_sparse_moe.experts.2.w1", |
|
"model.layers.7.block_sparse_moe.experts.2.w2", |
|
"model.layers.7.block_sparse_moe.experts.2.w3", |
|
"model.layers.7.block_sparse_moe.experts.3.w1", |
|
"model.layers.7.block_sparse_moe.experts.3.w2", |
|
"model.layers.7.block_sparse_moe.experts.3.w3", |
|
"model.layers.7.block_sparse_moe.experts.4.w1", |
|
"model.layers.7.block_sparse_moe.experts.4.w2", |
|
"model.layers.7.block_sparse_moe.experts.4.w3", |
|
"model.layers.7.block_sparse_moe.experts.5.w1", |
|
"model.layers.7.block_sparse_moe.experts.5.w2", |
|
"model.layers.7.block_sparse_moe.experts.5.w3", |
|
"model.layers.7.block_sparse_moe.experts.6.w1", |
|
"model.layers.7.block_sparse_moe.experts.6.w2", |
|
"model.layers.7.block_sparse_moe.experts.6.w3", |
|
"model.layers.7.block_sparse_moe.experts.7.w1", |
|
"model.layers.7.block_sparse_moe.experts.7.w2", |
|
"model.layers.7.block_sparse_moe.experts.7.w3", |
|
"model.layers.8.self_attn.q_proj", |
|
"model.layers.8.self_attn.k_proj", |
|
"model.layers.8.self_attn.v_proj", |
|
"model.layers.8.self_attn.o_proj", |
|
"model.layers.8.block_sparse_moe.gate", |
|
"model.layers.8.block_sparse_moe.experts.0.w1", |
|
"model.layers.8.block_sparse_moe.experts.0.w2", |
|
"model.layers.8.block_sparse_moe.experts.0.w3", |
|
"model.layers.8.block_sparse_moe.experts.1.w1", |
|
"model.layers.8.block_sparse_moe.experts.1.w2", |
|
"model.layers.8.block_sparse_moe.experts.1.w3", |
|
"model.layers.8.block_sparse_moe.experts.2.w1", |
|
"model.layers.8.block_sparse_moe.experts.2.w2", |
|
"model.layers.8.block_sparse_moe.experts.2.w3", |
|
"model.layers.8.block_sparse_moe.experts.3.w1", |
|
"model.layers.8.block_sparse_moe.experts.3.w2", |
|
"model.layers.8.block_sparse_moe.experts.3.w3", |
|
"model.layers.8.block_sparse_moe.experts.4.w1", |
|
"model.layers.8.block_sparse_moe.experts.4.w2", |
|
"model.layers.8.block_sparse_moe.experts.4.w3", |
|
"model.layers.8.block_sparse_moe.experts.5.w1", |
|
"model.layers.8.block_sparse_moe.experts.5.w2", |
|
"model.layers.8.block_sparse_moe.experts.5.w3", |
|
"model.layers.8.block_sparse_moe.experts.6.w1", |
|
"model.layers.8.block_sparse_moe.experts.6.w2", |
|
"model.layers.8.block_sparse_moe.experts.6.w3", |
|
"model.layers.8.block_sparse_moe.experts.7.w1", |
|
"model.layers.8.block_sparse_moe.experts.7.w2", |
|
"model.layers.8.block_sparse_moe.experts.7.w3", |
|
"model.layers.9.self_attn.q_proj", |
|
"model.layers.9.self_attn.k_proj", |
|
"model.layers.9.self_attn.v_proj", |
|
"model.layers.9.self_attn.o_proj", |
|
"model.layers.9.block_sparse_moe.gate", |
|
"model.layers.9.block_sparse_moe.experts.0.w1", |
|
"model.layers.9.block_sparse_moe.experts.0.w2", |
|
"model.layers.9.block_sparse_moe.experts.0.w3", |
|
"model.layers.9.block_sparse_moe.experts.1.w1", |
|
"model.layers.9.block_sparse_moe.experts.1.w2", |
|
"model.layers.9.block_sparse_moe.experts.1.w3", |
|
"model.layers.9.block_sparse_moe.experts.2.w1", |
|
"model.layers.9.block_sparse_moe.experts.2.w2", |
|
"model.layers.9.block_sparse_moe.experts.2.w3", |
|
"model.layers.9.block_sparse_moe.experts.3.w1", |
|
"model.layers.9.block_sparse_moe.experts.3.w2", |
|
"model.layers.9.block_sparse_moe.experts.3.w3", |
|
"model.layers.9.block_sparse_moe.experts.4.w1", |
|
"model.layers.9.block_sparse_moe.experts.4.w2", |
|
"model.layers.9.block_sparse_moe.experts.4.w3", |
|
"model.layers.9.block_sparse_moe.experts.5.w1", |
|
"model.layers.9.block_sparse_moe.experts.5.w2", |
|
"model.layers.9.block_sparse_moe.experts.5.w3", |
|
"model.layers.9.block_sparse_moe.experts.6.w1", |
|
"model.layers.9.block_sparse_moe.experts.6.w2", |
|
"model.layers.9.block_sparse_moe.experts.6.w3", |
|
"model.layers.9.block_sparse_moe.experts.7.w1", |
|
"model.layers.9.block_sparse_moe.experts.7.w2", |
|
"model.layers.9.block_sparse_moe.experts.7.w3", |
|
"model.layers.10.self_attn.q_proj", |
|
"model.layers.10.self_attn.k_proj", |
|
"model.layers.10.self_attn.v_proj", |
|
"model.layers.10.self_attn.o_proj", |
|
"model.layers.10.block_sparse_moe.gate", |
|
"model.layers.10.block_sparse_moe.experts.0.w1", |
|
"model.layers.10.block_sparse_moe.experts.0.w2", |
|
"model.layers.10.block_sparse_moe.experts.0.w3", |
|
"model.layers.10.block_sparse_moe.experts.1.w1", |
|
"model.layers.10.block_sparse_moe.experts.1.w2", |
|
"model.layers.10.block_sparse_moe.experts.1.w3", |
|
"model.layers.10.block_sparse_moe.experts.2.w1", |
|
"model.layers.10.block_sparse_moe.experts.2.w2", |
|
"model.layers.10.block_sparse_moe.experts.2.w3", |
|
"model.layers.10.block_sparse_moe.experts.3.w1", |
|
"model.layers.10.block_sparse_moe.experts.3.w2", |
|
"model.layers.10.block_sparse_moe.experts.3.w3", |
|
"model.layers.10.block_sparse_moe.experts.4.w1", |
|
"model.layers.10.block_sparse_moe.experts.4.w2", |
|
"model.layers.10.block_sparse_moe.experts.4.w3", |
|
"model.layers.10.block_sparse_moe.experts.5.w1", |
|
"model.layers.10.block_sparse_moe.experts.5.w2", |
|
"model.layers.10.block_sparse_moe.experts.5.w3", |
|
"model.layers.10.block_sparse_moe.experts.6.w1", |
|
"model.layers.10.block_sparse_moe.experts.6.w2", |
|
"model.layers.10.block_sparse_moe.experts.6.w3", |
|
"model.layers.10.block_sparse_moe.experts.7.w1", |
|
"model.layers.10.block_sparse_moe.experts.7.w2", |
|
"model.layers.10.block_sparse_moe.experts.7.w3", |
|
"model.layers.11.self_attn.q_proj", |
|
"model.layers.11.self_attn.k_proj", |
|
"model.layers.11.self_attn.v_proj", |
|
"model.layers.11.self_attn.o_proj", |
|
"model.layers.11.block_sparse_moe.gate", |
|
"model.layers.11.block_sparse_moe.experts.0.w1", |
|
"model.layers.11.block_sparse_moe.experts.0.w2", |
|
"model.layers.11.block_sparse_moe.experts.0.w3", |
|
"model.layers.11.block_sparse_moe.experts.1.w1", |
|
"model.layers.11.block_sparse_moe.experts.1.w2", |
|
"model.layers.11.block_sparse_moe.experts.1.w3", |
|
"model.layers.11.block_sparse_moe.experts.2.w1", |
|
"model.layers.11.block_sparse_moe.experts.2.w2", |
|
"model.layers.11.block_sparse_moe.experts.2.w3", |
|
"model.layers.11.block_sparse_moe.experts.3.w1", |
|
"model.layers.11.block_sparse_moe.experts.3.w2", |
|
"model.layers.11.block_sparse_moe.experts.3.w3", |
|
"model.layers.11.block_sparse_moe.experts.4.w1", |
|
"model.layers.11.block_sparse_moe.experts.4.w2", |
|
"model.layers.11.block_sparse_moe.experts.4.w3", |
|
"model.layers.11.block_sparse_moe.experts.5.w1", |
|
"model.layers.11.block_sparse_moe.experts.5.w2", |
|
"model.layers.11.block_sparse_moe.experts.5.w3", |
|
"model.layers.11.block_sparse_moe.experts.6.w1", |
|
"model.layers.11.block_sparse_moe.experts.6.w2", |
|
"model.layers.11.block_sparse_moe.experts.6.w3", |
|
"model.layers.11.block_sparse_moe.experts.7.w1", |
|
"model.layers.11.block_sparse_moe.experts.7.w2", |
|
"model.layers.11.block_sparse_moe.experts.7.w3", |
|
"model.layers.12.self_attn.q_proj", |
|
"model.layers.12.self_attn.k_proj", |
|
"model.layers.12.self_attn.v_proj", |
|
"model.layers.12.self_attn.o_proj", |
|
"model.layers.12.block_sparse_moe.gate", |
|
"model.layers.12.block_sparse_moe.experts.0.w1", |
|
"model.layers.12.block_sparse_moe.experts.0.w2", |
|
"model.layers.12.block_sparse_moe.experts.0.w3", |
|
"model.layers.12.block_sparse_moe.experts.1.w1", |
|
"model.layers.12.block_sparse_moe.experts.1.w2", |
|
"model.layers.12.block_sparse_moe.experts.1.w3", |
|
"model.layers.12.block_sparse_moe.experts.2.w1", |
|
"model.layers.12.block_sparse_moe.experts.2.w2", |
|
"model.layers.12.block_sparse_moe.experts.2.w3", |
|
"model.layers.12.block_sparse_moe.experts.3.w1", |
|
"model.layers.12.block_sparse_moe.experts.3.w2", |
|
"model.layers.12.block_sparse_moe.experts.3.w3", |
|
"model.layers.12.block_sparse_moe.experts.4.w1", |
|
"model.layers.12.block_sparse_moe.experts.4.w2", |
|
"model.layers.12.block_sparse_moe.experts.4.w3", |
|
"model.layers.12.block_sparse_moe.experts.5.w1", |
|
"model.layers.12.block_sparse_moe.experts.5.w2", |
|
"model.layers.12.block_sparse_moe.experts.5.w3", |
|
"model.layers.12.block_sparse_moe.experts.6.w1", |
|
"model.layers.12.block_sparse_moe.experts.6.w2", |
|
"model.layers.12.block_sparse_moe.experts.6.w3", |
|
"model.layers.12.block_sparse_moe.experts.7.w1", |
|
"model.layers.12.block_sparse_moe.experts.7.w2", |
|
"model.layers.12.block_sparse_moe.experts.7.w3", |
|
"model.layers.13.self_attn.q_proj", |
|
"model.layers.13.self_attn.k_proj", |
|
"model.layers.13.self_attn.v_proj", |
|
"model.layers.13.self_attn.o_proj", |
|
"model.layers.13.block_sparse_moe.gate", |
|
"model.layers.13.block_sparse_moe.experts.0.w1", |
|
"model.layers.13.block_sparse_moe.experts.0.w2", |
|
"model.layers.13.block_sparse_moe.experts.0.w3", |
|
"model.layers.13.block_sparse_moe.experts.1.w1", |
|
"model.layers.13.block_sparse_moe.experts.1.w2", |
|
"model.layers.13.block_sparse_moe.experts.1.w3", |
|
"model.layers.13.block_sparse_moe.experts.2.w1", |
|
"model.layers.13.block_sparse_moe.experts.2.w2", |
|
"model.layers.13.block_sparse_moe.experts.2.w3", |
|
"model.layers.13.block_sparse_moe.experts.3.w1", |
|
"model.layers.13.block_sparse_moe.experts.3.w2", |
|
"model.layers.13.block_sparse_moe.experts.3.w3", |
|
"model.layers.13.block_sparse_moe.experts.4.w1", |
|
"model.layers.13.block_sparse_moe.experts.4.w2", |
|
"model.layers.13.block_sparse_moe.experts.4.w3", |
|
"model.layers.13.block_sparse_moe.experts.5.w1", |
|
"model.layers.13.block_sparse_moe.experts.5.w2", |
|
"model.layers.13.block_sparse_moe.experts.5.w3", |
|
"model.layers.13.block_sparse_moe.experts.6.w1", |
|
"model.layers.13.block_sparse_moe.experts.6.w2", |
|
"model.layers.13.block_sparse_moe.experts.6.w3", |
|
"model.layers.13.block_sparse_moe.experts.7.w1", |
|
"model.layers.13.block_sparse_moe.experts.7.w2", |
|
"model.layers.13.block_sparse_moe.experts.7.w3", |
|
"model.layers.14.self_attn.q_proj", |
|
"model.layers.14.self_attn.k_proj", |
|
"model.layers.14.self_attn.v_proj", |
|
"model.layers.14.self_attn.o_proj", |
|
"model.layers.14.block_sparse_moe.gate", |
|
"model.layers.14.block_sparse_moe.experts.0.w1", |
|
"model.layers.14.block_sparse_moe.experts.0.w2", |
|
"model.layers.14.block_sparse_moe.experts.0.w3", |
|
"model.layers.14.block_sparse_moe.experts.1.w1", |
|
"model.layers.14.block_sparse_moe.experts.1.w2", |
|
"model.layers.14.block_sparse_moe.experts.1.w3", |
|
"model.layers.14.block_sparse_moe.experts.2.w1", |
|
"model.layers.14.block_sparse_moe.experts.2.w2", |
|
"model.layers.14.block_sparse_moe.experts.2.w3", |
|
"model.layers.14.block_sparse_moe.experts.3.w1", |
|
"model.layers.14.block_sparse_moe.experts.3.w2", |
|
"model.layers.14.block_sparse_moe.experts.3.w3", |
|
"model.layers.14.block_sparse_moe.experts.4.w1", |
|
"model.layers.14.block_sparse_moe.experts.4.w2", |
|
"model.layers.14.block_sparse_moe.experts.4.w3", |
|
"model.layers.14.block_sparse_moe.experts.5.w1", |
|
"model.layers.14.block_sparse_moe.experts.5.w2", |
|
"model.layers.14.block_sparse_moe.experts.5.w3", |
|
"model.layers.14.block_sparse_moe.experts.6.w1", |
|
"model.layers.14.block_sparse_moe.experts.6.w2", |
|
"model.layers.14.block_sparse_moe.experts.6.w3", |
|
"model.layers.14.block_sparse_moe.experts.7.w1", |
|
"model.layers.14.block_sparse_moe.experts.7.w2", |
|
"model.layers.14.block_sparse_moe.experts.7.w3", |
|
"model.layers.15.self_attn.q_proj", |
|
"model.layers.15.self_attn.k_proj", |
|
"model.layers.15.self_attn.v_proj", |
|
"model.layers.15.self_attn.o_proj", |
|
"model.layers.15.block_sparse_moe.gate", |
|
"model.layers.15.block_sparse_moe.experts.0.w1", |
|
"model.layers.15.block_sparse_moe.experts.0.w2", |
|
"model.layers.15.block_sparse_moe.experts.0.w3", |
|
"model.layers.15.block_sparse_moe.experts.1.w1", |
|
"model.layers.15.block_sparse_moe.experts.1.w2", |
|
"model.layers.15.block_sparse_moe.experts.1.w3", |
|
"model.layers.15.block_sparse_moe.experts.2.w1", |
|
"model.layers.15.block_sparse_moe.experts.2.w2", |
|
"model.layers.15.block_sparse_moe.experts.2.w3", |
|
"model.layers.15.block_sparse_moe.experts.3.w1", |
|
"model.layers.15.block_sparse_moe.experts.3.w2", |
|
"model.layers.15.block_sparse_moe.experts.3.w3", |
|
"model.layers.15.block_sparse_moe.experts.4.w1", |
|
"model.layers.15.block_sparse_moe.experts.4.w2", |
|
"model.layers.15.block_sparse_moe.experts.4.w3", |
|
"model.layers.15.block_sparse_moe.experts.5.w1", |
|
"model.layers.15.block_sparse_moe.experts.5.w2", |
|
"model.layers.15.block_sparse_moe.experts.5.w3", |
|
"model.layers.15.block_sparse_moe.experts.6.w1", |
|
"model.layers.15.block_sparse_moe.experts.6.w2", |
|
"model.layers.15.block_sparse_moe.experts.6.w3", |
|
"model.layers.15.block_sparse_moe.experts.7.w1", |
|
"model.layers.15.block_sparse_moe.experts.7.w2", |
|
"model.layers.15.block_sparse_moe.experts.7.w3", |
|
"model.layers.16.self_attn.q_proj", |
|
"model.layers.16.self_attn.k_proj", |
|
"model.layers.16.self_attn.v_proj", |
|
"model.layers.16.self_attn.o_proj", |
|
"model.layers.16.block_sparse_moe.gate", |
|
"model.layers.16.block_sparse_moe.experts.0.w1", |
|
"model.layers.16.block_sparse_moe.experts.0.w2", |
|
"model.layers.16.block_sparse_moe.experts.0.w3", |
|
"model.layers.16.block_sparse_moe.experts.1.w1", |
|
"model.layers.16.block_sparse_moe.experts.1.w2", |
|
"model.layers.16.block_sparse_moe.experts.1.w3", |
|
"model.layers.16.block_sparse_moe.experts.2.w1", |
|
"model.layers.16.block_sparse_moe.experts.2.w2", |
|
"model.layers.16.block_sparse_moe.experts.2.w3", |
|
"model.layers.16.block_sparse_moe.experts.3.w1", |
|
"model.layers.16.block_sparse_moe.experts.3.w2", |
|
"model.layers.16.block_sparse_moe.experts.3.w3", |
|
"model.layers.16.block_sparse_moe.experts.4.w1", |
|
"model.layers.16.block_sparse_moe.experts.4.w2", |
|
"model.layers.16.block_sparse_moe.experts.4.w3", |
|
"model.layers.16.block_sparse_moe.experts.5.w1", |
|
"model.layers.16.block_sparse_moe.experts.5.w2", |
|
"model.layers.16.block_sparse_moe.experts.5.w3", |
|
"model.layers.16.block_sparse_moe.experts.6.w1", |
|
"model.layers.16.block_sparse_moe.experts.6.w2", |
|
"model.layers.16.block_sparse_moe.experts.6.w3", |
|
"model.layers.16.block_sparse_moe.experts.7.w1", |
|
"model.layers.16.block_sparse_moe.experts.7.w2", |
|
"model.layers.16.block_sparse_moe.experts.7.w3", |
|
"model.layers.17.self_attn.q_proj", |
|
"model.layers.17.self_attn.k_proj", |
|
"model.layers.17.self_attn.v_proj", |
|
"model.layers.17.self_attn.o_proj", |
|
"model.layers.17.block_sparse_moe.gate", |
|
"model.layers.17.block_sparse_moe.experts.0.w1", |
|
"model.layers.17.block_sparse_moe.experts.0.w2", |
|
"model.layers.17.block_sparse_moe.experts.0.w3", |
|
"model.layers.17.block_sparse_moe.experts.1.w1", |
|
"model.layers.17.block_sparse_moe.experts.1.w2", |
|
"model.layers.17.block_sparse_moe.experts.1.w3", |
|
"model.layers.17.block_sparse_moe.experts.2.w1", |
|
"model.layers.17.block_sparse_moe.experts.2.w2", |
|
"model.layers.17.block_sparse_moe.experts.2.w3", |
|
"model.layers.17.block_sparse_moe.experts.3.w1", |
|
"model.layers.17.block_sparse_moe.experts.3.w2", |
|
"model.layers.17.block_sparse_moe.experts.3.w3", |
|
"model.layers.17.block_sparse_moe.experts.4.w1", |
|
"model.layers.17.block_sparse_moe.experts.4.w2", |
|
"model.layers.17.block_sparse_moe.experts.4.w3", |
|
"model.layers.17.block_sparse_moe.experts.5.w1", |
|
"model.layers.17.block_sparse_moe.experts.5.w2", |
|
"model.layers.17.block_sparse_moe.experts.5.w3", |
|
"model.layers.17.block_sparse_moe.experts.6.w1", |
|
"model.layers.17.block_sparse_moe.experts.6.w2", |
|
"model.layers.17.block_sparse_moe.experts.6.w3", |
|
"model.layers.17.block_sparse_moe.experts.7.w1", |
|
"model.layers.17.block_sparse_moe.experts.7.w2", |
|
"model.layers.17.block_sparse_moe.experts.7.w3", |
|
"model.layers.18.self_attn.q_proj", |
|
"model.layers.18.self_attn.k_proj", |
|
"model.layers.18.self_attn.v_proj", |
|
"model.layers.18.self_attn.o_proj", |
|
"model.layers.18.block_sparse_moe.gate", |
|
"model.layers.18.block_sparse_moe.experts.0.w1", |
|
"model.layers.18.block_sparse_moe.experts.0.w2", |
|
"model.layers.18.block_sparse_moe.experts.0.w3", |
|
"model.layers.18.block_sparse_moe.experts.1.w1", |
|
"model.layers.18.block_sparse_moe.experts.1.w2", |
|
"model.layers.18.block_sparse_moe.experts.1.w3", |
|
"model.layers.18.block_sparse_moe.experts.2.w1", |
|
"model.layers.18.block_sparse_moe.experts.2.w2", |
|
"model.layers.18.block_sparse_moe.experts.2.w3", |
|
"model.layers.18.block_sparse_moe.experts.3.w1", |
|
"model.layers.18.block_sparse_moe.experts.3.w2", |
|
"model.layers.18.block_sparse_moe.experts.3.w3", |
|
"model.layers.18.block_sparse_moe.experts.4.w1", |
|
"model.layers.18.block_sparse_moe.experts.4.w2", |
|
"model.layers.18.block_sparse_moe.experts.4.w3", |
|
"model.layers.18.block_sparse_moe.experts.5.w1", |
|
"model.layers.18.block_sparse_moe.experts.5.w2", |
|
"model.layers.18.block_sparse_moe.experts.5.w3", |
|
"model.layers.18.block_sparse_moe.experts.6.w1", |
|
"model.layers.18.block_sparse_moe.experts.6.w2", |
|
"model.layers.18.block_sparse_moe.experts.6.w3", |
|
"model.layers.18.block_sparse_moe.experts.7.w1", |
|
"model.layers.18.block_sparse_moe.experts.7.w2", |
|
"model.layers.18.block_sparse_moe.experts.7.w3", |
|
"model.layers.19.self_attn.q_proj", |
|
"model.layers.19.self_attn.k_proj", |
|
"model.layers.19.self_attn.v_proj", |
|
"model.layers.19.self_attn.o_proj", |
|
"model.layers.19.block_sparse_moe.gate", |
|
"model.layers.19.block_sparse_moe.experts.0.w1", |
|
"model.layers.19.block_sparse_moe.experts.0.w2", |
|
"model.layers.19.block_sparse_moe.experts.0.w3", |
|
"model.layers.19.block_sparse_moe.experts.1.w1", |
|
"model.layers.19.block_sparse_moe.experts.1.w2", |
|
"model.layers.19.block_sparse_moe.experts.1.w3", |
|
"model.layers.19.block_sparse_moe.experts.2.w1", |
|
"model.layers.19.block_sparse_moe.experts.2.w2", |
|
"model.layers.19.block_sparse_moe.experts.2.w3", |
|
"model.layers.19.block_sparse_moe.experts.3.w1", |
|
"model.layers.19.block_sparse_moe.experts.3.w2", |
|
"model.layers.19.block_sparse_moe.experts.3.w3", |
|
"model.layers.19.block_sparse_moe.experts.4.w1", |
|
"model.layers.19.block_sparse_moe.experts.4.w2", |
|
"model.layers.19.block_sparse_moe.experts.4.w3", |
|
"model.layers.19.block_sparse_moe.experts.5.w1", |
|
"model.layers.19.block_sparse_moe.experts.5.w2", |
|
"model.layers.19.block_sparse_moe.experts.5.w3", |
|
"model.layers.19.block_sparse_moe.experts.6.w1", |
|
"model.layers.19.block_sparse_moe.experts.6.w2", |
|
"model.layers.19.block_sparse_moe.experts.6.w3", |
|
"model.layers.19.block_sparse_moe.experts.7.w1", |
|
"model.layers.19.block_sparse_moe.experts.7.w2", |
|
"model.layers.19.block_sparse_moe.experts.7.w3", |
|
"model.layers.20.self_attn.q_proj", |
|
"model.layers.20.self_attn.k_proj", |
|
"model.layers.20.self_attn.v_proj", |
|
"model.layers.20.self_attn.o_proj", |
|
"model.layers.20.block_sparse_moe.gate", |
|
"model.layers.20.block_sparse_moe.experts.0.w1", |
|
"model.layers.20.block_sparse_moe.experts.0.w2", |
|
"model.layers.20.block_sparse_moe.experts.0.w3", |
|
"model.layers.20.block_sparse_moe.experts.1.w1", |
|
"model.layers.20.block_sparse_moe.experts.1.w2", |
|
"model.layers.20.block_sparse_moe.experts.1.w3", |
|
"model.layers.20.block_sparse_moe.experts.2.w1", |
|
"model.layers.20.block_sparse_moe.experts.2.w2", |
|
"model.layers.20.block_sparse_moe.experts.2.w3", |
|
"model.layers.20.block_sparse_moe.experts.3.w1", |
|
"model.layers.20.block_sparse_moe.experts.3.w2", |
|
"model.layers.20.block_sparse_moe.experts.3.w3", |
|
"model.layers.20.block_sparse_moe.experts.4.w1", |
|
"model.layers.20.block_sparse_moe.experts.4.w2", |
|
"model.layers.20.block_sparse_moe.experts.4.w3", |
|
"model.layers.20.block_sparse_moe.experts.5.w1", |
|
"model.layers.20.block_sparse_moe.experts.5.w2", |
|
"model.layers.20.block_sparse_moe.experts.5.w3", |
|
"model.layers.20.block_sparse_moe.experts.6.w1", |
|
"model.layers.20.block_sparse_moe.experts.6.w2", |
|
"model.layers.20.block_sparse_moe.experts.6.w3", |
|
"model.layers.20.block_sparse_moe.experts.7.w1", |
|
"model.layers.20.block_sparse_moe.experts.7.w2", |
|
"model.layers.20.block_sparse_moe.experts.7.w3", |
|
"model.layers.21.self_attn.q_proj", |
|
"model.layers.21.self_attn.k_proj", |
|
"model.layers.21.self_attn.v_proj", |
|
"model.layers.21.self_attn.o_proj", |
|
"model.layers.21.block_sparse_moe.gate", |
|
"model.layers.21.block_sparse_moe.experts.0.w1", |
|
"model.layers.21.block_sparse_moe.experts.0.w2", |
|
"model.layers.21.block_sparse_moe.experts.0.w3", |
|
"model.layers.21.block_sparse_moe.experts.1.w1", |
|
"model.layers.21.block_sparse_moe.experts.1.w2", |
|
"model.layers.21.block_sparse_moe.experts.1.w3", |
|
"model.layers.21.block_sparse_moe.experts.2.w1", |
|
"model.layers.21.block_sparse_moe.experts.2.w2", |
|
"model.layers.21.block_sparse_moe.experts.2.w3", |
|
"model.layers.21.block_sparse_moe.experts.3.w1", |
|
"model.layers.21.block_sparse_moe.experts.3.w2", |
|
"model.layers.21.block_sparse_moe.experts.3.w3", |
|
"model.layers.21.block_sparse_moe.experts.4.w1", |
|
"model.layers.21.block_sparse_moe.experts.4.w2", |
|
"model.layers.21.block_sparse_moe.experts.4.w3", |
|
"model.layers.21.block_sparse_moe.experts.5.w1", |
|
"model.layers.21.block_sparse_moe.experts.5.w2", |
|
"model.layers.21.block_sparse_moe.experts.5.w3", |
|
"model.layers.21.block_sparse_moe.experts.6.w1", |
|
"model.layers.21.block_sparse_moe.experts.6.w2", |
|
"model.layers.21.block_sparse_moe.experts.6.w3", |
|
"model.layers.21.block_sparse_moe.experts.7.w1", |
|
"model.layers.21.block_sparse_moe.experts.7.w2", |
|
"model.layers.21.block_sparse_moe.experts.7.w3", |
|
"model.layers.22.self_attn.q_proj", |
|
"model.layers.22.self_attn.k_proj", |
|
"model.layers.22.self_attn.v_proj", |
|
"model.layers.22.self_attn.o_proj", |
|
"model.layers.22.block_sparse_moe.gate", |
|
"model.layers.22.block_sparse_moe.experts.0.w1", |
|
"model.layers.22.block_sparse_moe.experts.0.w2", |
|
"model.layers.22.block_sparse_moe.experts.0.w3", |
|
"model.layers.22.block_sparse_moe.experts.1.w1", |
|
"model.layers.22.block_sparse_moe.experts.1.w2", |
|
"model.layers.22.block_sparse_moe.experts.1.w3", |
|
"model.layers.22.block_sparse_moe.experts.2.w1", |
|
"model.layers.22.block_sparse_moe.experts.2.w2", |
|
"model.layers.22.block_sparse_moe.experts.2.w3", |
|
"model.layers.22.block_sparse_moe.experts.3.w1", |
|
"model.layers.22.block_sparse_moe.experts.3.w2", |
|
"model.layers.22.block_sparse_moe.experts.3.w3", |
|
"model.layers.22.block_sparse_moe.experts.4.w1", |
|
"model.layers.22.block_sparse_moe.experts.4.w2", |
|
"model.layers.22.block_sparse_moe.experts.4.w3", |
|
"model.layers.22.block_sparse_moe.experts.5.w1", |
|
"model.layers.22.block_sparse_moe.experts.5.w2", |
|
"model.layers.22.block_sparse_moe.experts.5.w3", |
|
"model.layers.22.block_sparse_moe.experts.6.w1", |
|
"model.layers.22.block_sparse_moe.experts.6.w2", |
|
"model.layers.22.block_sparse_moe.experts.6.w3", |
|
"model.layers.22.block_sparse_moe.experts.7.w1", |
|
"model.layers.22.block_sparse_moe.experts.7.w2", |
|
"model.layers.22.block_sparse_moe.experts.7.w3", |
|
"model.layers.23.self_attn.q_proj", |
|
"model.layers.23.self_attn.k_proj", |
|
"model.layers.23.self_attn.v_proj", |
|
"model.layers.23.self_attn.o_proj", |
|
"model.layers.23.block_sparse_moe.gate", |
|
"model.layers.23.block_sparse_moe.experts.0.w1", |
|
"model.layers.23.block_sparse_moe.experts.0.w2", |
|
"model.layers.23.block_sparse_moe.experts.0.w3", |
|
"model.layers.23.block_sparse_moe.experts.1.w1", |
|
"model.layers.23.block_sparse_moe.experts.1.w2", |
|
"model.layers.23.block_sparse_moe.experts.1.w3", |
|
"model.layers.23.block_sparse_moe.experts.2.w1", |
|
"model.layers.23.block_sparse_moe.experts.2.w2", |
|
"model.layers.23.block_sparse_moe.experts.2.w3", |
|
"model.layers.23.block_sparse_moe.experts.3.w1", |
|
"model.layers.23.block_sparse_moe.experts.3.w2", |
|
"model.layers.23.block_sparse_moe.experts.3.w3", |
|
"model.layers.23.block_sparse_moe.experts.4.w1", |
|
"model.layers.23.block_sparse_moe.experts.4.w2", |
|
"model.layers.23.block_sparse_moe.experts.4.w3", |
|
"model.layers.23.block_sparse_moe.experts.5.w1", |
|
"model.layers.23.block_sparse_moe.experts.5.w2", |
|
"model.layers.23.block_sparse_moe.experts.5.w3", |
|
"model.layers.23.block_sparse_moe.experts.6.w1", |
|
"model.layers.23.block_sparse_moe.experts.6.w2", |
|
"model.layers.23.block_sparse_moe.experts.6.w3", |
|
"model.layers.23.block_sparse_moe.experts.7.w1", |
|
"model.layers.23.block_sparse_moe.experts.7.w2", |
|
"model.layers.23.block_sparse_moe.experts.7.w3", |
|
"model.layers.24.self_attn.q_proj", |
|
"model.layers.24.self_attn.k_proj", |
|
"model.layers.24.self_attn.v_proj", |
|
"model.layers.24.self_attn.o_proj", |
|
"model.layers.24.block_sparse_moe.gate", |
|
"model.layers.24.block_sparse_moe.experts.0.w1", |
|
"model.layers.24.block_sparse_moe.experts.0.w2", |
|
"model.layers.24.block_sparse_moe.experts.0.w3", |
|
"model.layers.24.block_sparse_moe.experts.1.w1", |
|
"model.layers.24.block_sparse_moe.experts.1.w2", |
|
"model.layers.24.block_sparse_moe.experts.1.w3", |
|
"model.layers.24.block_sparse_moe.experts.2.w1", |
|
"model.layers.24.block_sparse_moe.experts.2.w2", |
|
"model.layers.24.block_sparse_moe.experts.2.w3", |
|
"model.layers.24.block_sparse_moe.experts.3.w1", |
|
"model.layers.24.block_sparse_moe.experts.3.w2", |
|
"model.layers.24.block_sparse_moe.experts.3.w3", |
|
"model.layers.24.block_sparse_moe.experts.4.w1", |
|
"model.layers.24.block_sparse_moe.experts.4.w2", |
|
"model.layers.24.block_sparse_moe.experts.4.w3", |
|
"model.layers.24.block_sparse_moe.experts.5.w1", |
|
"model.layers.24.block_sparse_moe.experts.5.w2", |
|
"model.layers.24.block_sparse_moe.experts.5.w3", |
|
"model.layers.24.block_sparse_moe.experts.6.w1", |
|
"model.layers.24.block_sparse_moe.experts.6.w2", |
|
"model.layers.24.block_sparse_moe.experts.6.w3", |
|
"model.layers.24.block_sparse_moe.experts.7.w1", |
|
"model.layers.24.block_sparse_moe.experts.7.w2", |
|
"model.layers.24.block_sparse_moe.experts.7.w3", |
|
"model.layers.25.self_attn.q_proj", |
|
"model.layers.25.self_attn.k_proj", |
|
"model.layers.25.self_attn.v_proj", |
|
"model.layers.25.self_attn.o_proj", |
|
"model.layers.25.block_sparse_moe.gate", |
|
"model.layers.25.block_sparse_moe.experts.0.w1", |
|
"model.layers.25.block_sparse_moe.experts.0.w2", |
|
"model.layers.25.block_sparse_moe.experts.0.w3", |
|
"model.layers.25.block_sparse_moe.experts.1.w1", |
|
"model.layers.25.block_sparse_moe.experts.1.w2", |
|
"model.layers.25.block_sparse_moe.experts.1.w3", |
|
"model.layers.25.block_sparse_moe.experts.2.w1", |
|
"model.layers.25.block_sparse_moe.experts.2.w2", |
|
"model.layers.25.block_sparse_moe.experts.2.w3", |
|
"model.layers.25.block_sparse_moe.experts.3.w1", |
|
"model.layers.25.block_sparse_moe.experts.3.w2", |
|
"model.layers.25.block_sparse_moe.experts.3.w3", |
|
"model.layers.25.block_sparse_moe.experts.4.w1", |
|
"model.layers.25.block_sparse_moe.experts.4.w2", |
|
"model.layers.25.block_sparse_moe.experts.4.w3", |
|
"model.layers.25.block_sparse_moe.experts.5.w1", |
|
"model.layers.25.block_sparse_moe.experts.5.w2", |
|
"model.layers.25.block_sparse_moe.experts.5.w3", |
|
"model.layers.25.block_sparse_moe.experts.6.w1", |
|
"model.layers.25.block_sparse_moe.experts.6.w2", |
|
"model.layers.25.block_sparse_moe.experts.6.w3", |
|
"model.layers.25.block_sparse_moe.experts.7.w1", |
|
"model.layers.25.block_sparse_moe.experts.7.w2", |
|
"model.layers.25.block_sparse_moe.experts.7.w3", |
|
"model.layers.26.self_attn.q_proj", |
|
"model.layers.26.self_attn.k_proj", |
|
"model.layers.26.self_attn.v_proj", |
|
"model.layers.26.self_attn.o_proj", |
|
"model.layers.26.block_sparse_moe.gate", |
|
"model.layers.26.block_sparse_moe.experts.0.w1", |
|
"model.layers.26.block_sparse_moe.experts.0.w2", |
|
"model.layers.26.block_sparse_moe.experts.0.w3", |
|
"model.layers.26.block_sparse_moe.experts.1.w1", |
|
"model.layers.26.block_sparse_moe.experts.1.w2", |
|
"model.layers.26.block_sparse_moe.experts.1.w3", |
|
"model.layers.26.block_sparse_moe.experts.2.w1", |
|
"model.layers.26.block_sparse_moe.experts.2.w2", |
|
"model.layers.26.block_sparse_moe.experts.2.w3", |
|
"model.layers.26.block_sparse_moe.experts.3.w1", |
|
"model.layers.26.block_sparse_moe.experts.3.w2", |
|
"model.layers.26.block_sparse_moe.experts.3.w3", |
|
"model.layers.26.block_sparse_moe.experts.4.w1", |
|
"model.layers.26.block_sparse_moe.experts.4.w2", |
|
"model.layers.26.block_sparse_moe.experts.4.w3", |
|
"model.layers.26.block_sparse_moe.experts.5.w1", |
|
"model.layers.26.block_sparse_moe.experts.5.w2", |
|
"model.layers.26.block_sparse_moe.experts.5.w3", |
|
"model.layers.26.block_sparse_moe.experts.6.w1", |
|
"model.layers.26.block_sparse_moe.experts.6.w2", |
|
"model.layers.26.block_sparse_moe.experts.6.w3", |
|
"model.layers.26.block_sparse_moe.experts.7.w1", |
|
"model.layers.26.block_sparse_moe.experts.7.w2", |
|
"model.layers.26.block_sparse_moe.experts.7.w3", |
|
"model.layers.27.self_attn.q_proj", |
|
"model.layers.27.self_attn.k_proj", |
|
"model.layers.27.self_attn.v_proj", |
|
"model.layers.27.self_attn.o_proj", |
|
"model.layers.27.block_sparse_moe.gate", |
|
"model.layers.27.block_sparse_moe.experts.0.w1", |
|
"model.layers.27.block_sparse_moe.experts.0.w2", |
|
"model.layers.27.block_sparse_moe.experts.0.w3", |
|
"model.layers.27.block_sparse_moe.experts.1.w1", |
|
"model.layers.27.block_sparse_moe.experts.1.w2", |
|
"model.layers.27.block_sparse_moe.experts.1.w3", |
|
"model.layers.27.block_sparse_moe.experts.2.w1", |
|
"model.layers.27.block_sparse_moe.experts.2.w2", |
|
"model.layers.27.block_sparse_moe.experts.2.w3", |
|
"model.layers.27.block_sparse_moe.experts.3.w1", |
|
"model.layers.27.block_sparse_moe.experts.3.w2", |
|
"model.layers.27.block_sparse_moe.experts.3.w3", |
|
"model.layers.27.block_sparse_moe.experts.4.w1", |
|
"model.layers.27.block_sparse_moe.experts.4.w2", |
|
"model.layers.27.block_sparse_moe.experts.4.w3", |
|
"model.layers.27.block_sparse_moe.experts.5.w1", |
|
"model.layers.27.block_sparse_moe.experts.5.w2", |
|
"model.layers.27.block_sparse_moe.experts.5.w3", |
|
"model.layers.27.block_sparse_moe.experts.6.w1", |
|
"model.layers.27.block_sparse_moe.experts.6.w2", |
|
"model.layers.27.block_sparse_moe.experts.6.w3", |
|
"model.layers.27.block_sparse_moe.experts.7.w1", |
|
"model.layers.27.block_sparse_moe.experts.7.w2", |
|
"model.layers.27.block_sparse_moe.experts.7.w3", |
|
"model.layers.28.self_attn.q_proj", |
|
"model.layers.28.self_attn.k_proj", |
|
"model.layers.28.self_attn.v_proj", |
|
"model.layers.28.self_attn.o_proj", |
|
"model.layers.28.block_sparse_moe.gate", |
|
"model.layers.28.block_sparse_moe.experts.0.w1", |
|
"model.layers.28.block_sparse_moe.experts.0.w2", |
|
"model.layers.28.block_sparse_moe.experts.0.w3", |
|
"model.layers.28.block_sparse_moe.experts.1.w1", |
|
"model.layers.28.block_sparse_moe.experts.1.w2", |
|
"model.layers.28.block_sparse_moe.experts.1.w3", |
|
"model.layers.28.block_sparse_moe.experts.2.w1", |
|
"model.layers.28.block_sparse_moe.experts.2.w2", |
|
"model.layers.28.block_sparse_moe.experts.2.w3", |
|
"model.layers.28.block_sparse_moe.experts.3.w1", |
|
"model.layers.28.block_sparse_moe.experts.3.w2", |
|
"model.layers.28.block_sparse_moe.experts.3.w3", |
|
"model.layers.28.block_sparse_moe.experts.4.w1", |
|
"model.layers.28.block_sparse_moe.experts.4.w2", |
|
"model.layers.28.block_sparse_moe.experts.4.w3", |
|
"model.layers.28.block_sparse_moe.experts.5.w1", |
|
"model.layers.28.block_sparse_moe.experts.5.w2", |
|
"model.layers.28.block_sparse_moe.experts.5.w3", |
|
"model.layers.28.block_sparse_moe.experts.6.w1", |
|
"model.layers.28.block_sparse_moe.experts.6.w2", |
|
"model.layers.28.block_sparse_moe.experts.6.w3", |
|
"model.layers.28.block_sparse_moe.experts.7.w1", |
|
"model.layers.28.block_sparse_moe.experts.7.w2", |
|
"model.layers.28.block_sparse_moe.experts.7.w3", |
|
"model.layers.29.self_attn.q_proj", |
|
"model.layers.29.self_attn.k_proj", |
|
"model.layers.29.self_attn.v_proj", |
|
"model.layers.29.self_attn.o_proj", |
|
"model.layers.29.block_sparse_moe.gate", |
|
"model.layers.29.block_sparse_moe.experts.0.w1", |
|
"model.layers.29.block_sparse_moe.experts.0.w2", |
|
"model.layers.29.block_sparse_moe.experts.0.w3", |
|
"model.layers.29.block_sparse_moe.experts.1.w1", |
|
"model.layers.29.block_sparse_moe.experts.1.w2", |
|
"model.layers.29.block_sparse_moe.experts.1.w3", |
|
"model.layers.29.block_sparse_moe.experts.2.w1", |
|
"model.layers.29.block_sparse_moe.experts.2.w2", |
|
"model.layers.29.block_sparse_moe.experts.2.w3", |
|
"model.layers.29.block_sparse_moe.experts.3.w1", |
|
"model.layers.29.block_sparse_moe.experts.3.w2", |
|
"model.layers.29.block_sparse_moe.experts.3.w3", |
|
"model.layers.29.block_sparse_moe.experts.4.w1", |
|
"model.layers.29.block_sparse_moe.experts.4.w2", |
|
"model.layers.29.block_sparse_moe.experts.4.w3", |
|
"model.layers.29.block_sparse_moe.experts.5.w1", |
|
"model.layers.29.block_sparse_moe.experts.5.w2", |
|
"model.layers.29.block_sparse_moe.experts.5.w3", |
|
"model.layers.29.block_sparse_moe.experts.6.w1", |
|
"model.layers.29.block_sparse_moe.experts.6.w2", |
|
"model.layers.29.block_sparse_moe.experts.6.w3", |
|
"model.layers.29.block_sparse_moe.experts.7.w1", |
|
"model.layers.29.block_sparse_moe.experts.7.w2", |
|
"model.layers.29.block_sparse_moe.experts.7.w3", |
|
"model.layers.30.self_attn.q_proj", |
|
"model.layers.30.self_attn.k_proj", |
|
"model.layers.30.self_attn.v_proj", |
|
"model.layers.30.self_attn.o_proj", |
|
"model.layers.30.block_sparse_moe.gate", |
|
"model.layers.30.block_sparse_moe.experts.0.w1", |
|
"model.layers.30.block_sparse_moe.experts.0.w2", |
|
"model.layers.30.block_sparse_moe.experts.0.w3", |
|
"model.layers.30.block_sparse_moe.experts.1.w1", |
|
"model.layers.30.block_sparse_moe.experts.1.w2", |
|
"model.layers.30.block_sparse_moe.experts.1.w3", |
|
"model.layers.30.block_sparse_moe.experts.2.w1", |
|
"model.layers.30.block_sparse_moe.experts.2.w2", |
|
"model.layers.30.block_sparse_moe.experts.2.w3", |
|
"model.layers.30.block_sparse_moe.experts.3.w1", |
|
"model.layers.30.block_sparse_moe.experts.3.w2", |
|
"model.layers.30.block_sparse_moe.experts.3.w3", |
|
"model.layers.30.block_sparse_moe.experts.4.w1", |
|
"model.layers.30.block_sparse_moe.experts.4.w2", |
|
"model.layers.30.block_sparse_moe.experts.4.w3", |
|
"model.layers.30.block_sparse_moe.experts.5.w1", |
|
"model.layers.30.block_sparse_moe.experts.5.w2", |
|
"model.layers.30.block_sparse_moe.experts.5.w3", |
|
"model.layers.30.block_sparse_moe.experts.6.w1", |
|
"model.layers.30.block_sparse_moe.experts.6.w2", |
|
"model.layers.30.block_sparse_moe.experts.6.w3", |
|
"model.layers.30.block_sparse_moe.experts.7.w1", |
|
"model.layers.30.block_sparse_moe.experts.7.w2", |
|
"model.layers.30.block_sparse_moe.experts.7.w3", |
|
"model.layers.31.self_attn.q_proj", |
|
"model.layers.31.self_attn.k_proj", |
|
"model.layers.31.self_attn.v_proj", |
|
"model.layers.31.self_attn.o_proj", |
|
"model.layers.31.block_sparse_moe.gate", |
|
"model.layers.31.block_sparse_moe.experts.0.w1", |
|
"model.layers.31.block_sparse_moe.experts.0.w2", |
|
"model.layers.31.block_sparse_moe.experts.0.w3", |
|
"model.layers.31.block_sparse_moe.experts.1.w1", |
|
"model.layers.31.block_sparse_moe.experts.1.w2", |
|
"model.layers.31.block_sparse_moe.experts.1.w3", |
|
"model.layers.31.block_sparse_moe.experts.2.w1", |
|
"model.layers.31.block_sparse_moe.experts.2.w2", |
|
"model.layers.31.block_sparse_moe.experts.2.w3", |
|
"model.layers.31.block_sparse_moe.experts.3.w1", |
|
"model.layers.31.block_sparse_moe.experts.3.w2", |
|
"model.layers.31.block_sparse_moe.experts.3.w3", |
|
"model.layers.31.block_sparse_moe.experts.4.w1", |
|
"model.layers.31.block_sparse_moe.experts.4.w2", |
|
"model.layers.31.block_sparse_moe.experts.4.w3", |
|
"model.layers.31.block_sparse_moe.experts.5.w1", |
|
"model.layers.31.block_sparse_moe.experts.5.w2", |
|
"model.layers.31.block_sparse_moe.experts.5.w3", |
|
"model.layers.31.block_sparse_moe.experts.6.w1", |
|
"model.layers.31.block_sparse_moe.experts.6.w2", |
|
"model.layers.31.block_sparse_moe.experts.6.w3", |
|
"model.layers.31.block_sparse_moe.experts.7.w1", |
|
"model.layers.31.block_sparse_moe.experts.7.w2", |
|
"model.layers.31.block_sparse_moe.experts.7.w3", |
|
"model.layers.32.self_attn.q_proj", |
|
"model.layers.32.self_attn.k_proj", |
|
"model.layers.32.self_attn.v_proj", |
|
"model.layers.32.self_attn.o_proj", |
|
"model.layers.32.block_sparse_moe.gate", |
|
"model.layers.32.block_sparse_moe.experts.0.w1", |
|
"model.layers.32.block_sparse_moe.experts.0.w2", |
|
"model.layers.32.block_sparse_moe.experts.0.w3", |
|
"model.layers.32.block_sparse_moe.experts.1.w1", |
|
"model.layers.32.block_sparse_moe.experts.1.w2", |
|
"model.layers.32.block_sparse_moe.experts.1.w3", |
|
"model.layers.32.block_sparse_moe.experts.2.w1", |
|
"model.layers.32.block_sparse_moe.experts.2.w2", |
|
"model.layers.32.block_sparse_moe.experts.2.w3", |
|
"model.layers.32.block_sparse_moe.experts.3.w1", |
|
"model.layers.32.block_sparse_moe.experts.3.w2", |
|
"model.layers.32.block_sparse_moe.experts.3.w3", |
|
"model.layers.32.block_sparse_moe.experts.4.w1", |
|
"model.layers.32.block_sparse_moe.experts.4.w2", |
|
"model.layers.32.block_sparse_moe.experts.4.w3", |
|
"model.layers.32.block_sparse_moe.experts.5.w1", |
|
"model.layers.32.block_sparse_moe.experts.5.w2", |
|
"model.layers.32.block_sparse_moe.experts.5.w3", |
|
"model.layers.32.block_sparse_moe.experts.6.w1", |
|
"model.layers.32.block_sparse_moe.experts.6.w2", |
|
"model.layers.32.block_sparse_moe.experts.6.w3", |
|
"model.layers.32.block_sparse_moe.experts.7.w1", |
|
"model.layers.32.block_sparse_moe.experts.7.w2", |
|
"model.layers.32.block_sparse_moe.experts.7.w3", |
|
"model.layers.33.self_attn.q_proj", |
|
"model.layers.33.self_attn.k_proj", |
|
"model.layers.33.self_attn.v_proj", |
|
"model.layers.33.self_attn.o_proj", |
|
"model.layers.33.block_sparse_moe.gate", |
|
"model.layers.33.block_sparse_moe.experts.0.w1", |
|
"model.layers.33.block_sparse_moe.experts.0.w2", |
|
"model.layers.33.block_sparse_moe.experts.0.w3", |
|
"model.layers.33.block_sparse_moe.experts.1.w1", |
|
"model.layers.33.block_sparse_moe.experts.1.w2", |
|
"model.layers.33.block_sparse_moe.experts.1.w3", |
|
"model.layers.33.block_sparse_moe.experts.2.w1", |
|
"model.layers.33.block_sparse_moe.experts.2.w2", |
|
"model.layers.33.block_sparse_moe.experts.2.w3", |
|
"model.layers.33.block_sparse_moe.experts.3.w1", |
|
"model.layers.33.block_sparse_moe.experts.3.w2", |
|
"model.layers.33.block_sparse_moe.experts.3.w3", |
|
"model.layers.33.block_sparse_moe.experts.4.w1", |
|
"model.layers.33.block_sparse_moe.experts.4.w2", |
|
"model.layers.33.block_sparse_moe.experts.4.w3", |
|
"model.layers.33.block_sparse_moe.experts.5.w1", |
|
"model.layers.33.block_sparse_moe.experts.5.w2", |
|
"model.layers.33.block_sparse_moe.experts.5.w3", |
|
"model.layers.33.block_sparse_moe.experts.6.w1", |
|
"model.layers.33.block_sparse_moe.experts.6.w2", |
|
"model.layers.33.block_sparse_moe.experts.6.w3", |
|
"model.layers.33.block_sparse_moe.experts.7.w1", |
|
"model.layers.33.block_sparse_moe.experts.7.w2", |
|
"model.layers.33.block_sparse_moe.experts.7.w3", |
|
"model.layers.34.self_attn.q_proj", |
|
"model.layers.34.self_attn.k_proj", |
|
"model.layers.34.self_attn.v_proj", |
|
"model.layers.34.self_attn.o_proj", |
|
"model.layers.34.block_sparse_moe.gate", |
|
"model.layers.34.block_sparse_moe.experts.0.w1", |
|
"model.layers.34.block_sparse_moe.experts.0.w2", |
|
"model.layers.34.block_sparse_moe.experts.0.w3", |
|
"model.layers.34.block_sparse_moe.experts.1.w1", |
|
"model.layers.34.block_sparse_moe.experts.1.w2", |
|
"model.layers.34.block_sparse_moe.experts.1.w3", |
|
"model.layers.34.block_sparse_moe.experts.2.w1", |
|
"model.layers.34.block_sparse_moe.experts.2.w2", |
|
"model.layers.34.block_sparse_moe.experts.2.w3", |
|
"model.layers.34.block_sparse_moe.experts.3.w1", |
|
"model.layers.34.block_sparse_moe.experts.3.w2", |
|
"model.layers.34.block_sparse_moe.experts.3.w3", |
|
"model.layers.34.block_sparse_moe.experts.4.w1", |
|
"model.layers.34.block_sparse_moe.experts.4.w2", |
|
"model.layers.34.block_sparse_moe.experts.4.w3", |
|
"model.layers.34.block_sparse_moe.experts.5.w1", |
|
"model.layers.34.block_sparse_moe.experts.5.w2", |
|
"model.layers.34.block_sparse_moe.experts.5.w3", |
|
"model.layers.34.block_sparse_moe.experts.6.w1", |
|
"model.layers.34.block_sparse_moe.experts.6.w2", |
|
"model.layers.34.block_sparse_moe.experts.6.w3", |
|
"model.layers.34.block_sparse_moe.experts.7.w1", |
|
"model.layers.34.block_sparse_moe.experts.7.w2", |
|
"model.layers.34.block_sparse_moe.experts.7.w3", |
|
"model.layers.35.self_attn.q_proj", |
|
"model.layers.35.self_attn.k_proj", |
|
"model.layers.35.self_attn.v_proj", |
|
"model.layers.35.self_attn.o_proj", |
|
"model.layers.35.block_sparse_moe.gate", |
|
"model.layers.35.block_sparse_moe.experts.0.w1", |
|
"model.layers.35.block_sparse_moe.experts.0.w2", |
|
"model.layers.35.block_sparse_moe.experts.0.w3", |
|
"model.layers.35.block_sparse_moe.experts.1.w1", |
|
"model.layers.35.block_sparse_moe.experts.1.w2", |
|
"model.layers.35.block_sparse_moe.experts.1.w3", |
|
"model.layers.35.block_sparse_moe.experts.2.w1", |
|
"model.layers.35.block_sparse_moe.experts.2.w2", |
|
"model.layers.35.block_sparse_moe.experts.2.w3", |
|
"model.layers.35.block_sparse_moe.experts.3.w1", |
|
"model.layers.35.block_sparse_moe.experts.3.w2", |
|
"model.layers.35.block_sparse_moe.experts.3.w3", |
|
"model.layers.35.block_sparse_moe.experts.4.w1", |
|
"model.layers.35.block_sparse_moe.experts.4.w2", |
|
"model.layers.35.block_sparse_moe.experts.4.w3", |
|
"model.layers.35.block_sparse_moe.experts.5.w1", |
|
"model.layers.35.block_sparse_moe.experts.5.w2", |
|
"model.layers.35.block_sparse_moe.experts.5.w3", |
|
"model.layers.35.block_sparse_moe.experts.6.w1", |
|
"model.layers.35.block_sparse_moe.experts.6.w2", |
|
"model.layers.35.block_sparse_moe.experts.6.w3", |
|
"model.layers.35.block_sparse_moe.experts.7.w1", |
|
"model.layers.35.block_sparse_moe.experts.7.w2", |
|
"model.layers.35.block_sparse_moe.experts.7.w3", |
|
"model.layers.36.self_attn.q_proj", |
|
"model.layers.36.self_attn.k_proj", |
|
"model.layers.36.self_attn.v_proj", |
|
"model.layers.36.self_attn.o_proj", |
|
"model.layers.36.block_sparse_moe.gate", |
|
"model.layers.36.block_sparse_moe.experts.0.w1", |
|
"model.layers.36.block_sparse_moe.experts.0.w2", |
|
"model.layers.36.block_sparse_moe.experts.0.w3", |
|
"model.layers.36.block_sparse_moe.experts.1.w1", |
|
"model.layers.36.block_sparse_moe.experts.1.w2", |
|
"model.layers.36.block_sparse_moe.experts.1.w3", |
|
"model.layers.36.block_sparse_moe.experts.2.w1", |
|
"model.layers.36.block_sparse_moe.experts.2.w2", |
|
"model.layers.36.block_sparse_moe.experts.2.w3", |
|
"model.layers.36.block_sparse_moe.experts.3.w1", |
|
"model.layers.36.block_sparse_moe.experts.3.w2", |
|
"model.layers.36.block_sparse_moe.experts.3.w3", |
|
"model.layers.36.block_sparse_moe.experts.4.w1", |
|
"model.layers.36.block_sparse_moe.experts.4.w2", |
|
"model.layers.36.block_sparse_moe.experts.4.w3", |
|
"model.layers.36.block_sparse_moe.experts.5.w1", |
|
"model.layers.36.block_sparse_moe.experts.5.w2", |
|
"model.layers.36.block_sparse_moe.experts.5.w3", |
|
"model.layers.36.block_sparse_moe.experts.6.w1", |
|
"model.layers.36.block_sparse_moe.experts.6.w2", |
|
"model.layers.36.block_sparse_moe.experts.6.w3", |
|
"model.layers.36.block_sparse_moe.experts.7.w1", |
|
"model.layers.36.block_sparse_moe.experts.7.w2", |
|
"model.layers.36.block_sparse_moe.experts.7.w3", |
|
"model.layers.37.self_attn.q_proj", |
|
"model.layers.37.self_attn.k_proj", |
|
"model.layers.37.self_attn.v_proj", |
|
"model.layers.37.self_attn.o_proj", |
|
"model.layers.37.block_sparse_moe.gate", |
|
"model.layers.37.block_sparse_moe.experts.0.w1", |
|
"model.layers.37.block_sparse_moe.experts.0.w2", |
|
"model.layers.37.block_sparse_moe.experts.0.w3", |
|
"model.layers.37.block_sparse_moe.experts.1.w1", |
|
"model.layers.37.block_sparse_moe.experts.1.w2", |
|
"model.layers.37.block_sparse_moe.experts.1.w3", |
|
"model.layers.37.block_sparse_moe.experts.2.w1", |
|
"model.layers.37.block_sparse_moe.experts.2.w2", |
|
"model.layers.37.block_sparse_moe.experts.2.w3", |
|
"model.layers.37.block_sparse_moe.experts.3.w1", |
|
"model.layers.37.block_sparse_moe.experts.3.w2", |
|
"model.layers.37.block_sparse_moe.experts.3.w3", |
|
"model.layers.37.block_sparse_moe.experts.4.w1", |
|
"model.layers.37.block_sparse_moe.experts.4.w2", |
|
"model.layers.37.block_sparse_moe.experts.4.w3", |
|
"model.layers.37.block_sparse_moe.experts.5.w1", |
|
"model.layers.37.block_sparse_moe.experts.5.w2", |
|
"model.layers.37.block_sparse_moe.experts.5.w3", |
|
"model.layers.37.block_sparse_moe.experts.6.w1", |
|
"model.layers.37.block_sparse_moe.experts.6.w2", |
|
"model.layers.37.block_sparse_moe.experts.6.w3", |
|
"model.layers.37.block_sparse_moe.experts.7.w1", |
|
"model.layers.37.block_sparse_moe.experts.7.w2", |
|
"model.layers.37.block_sparse_moe.experts.7.w3", |
|
"model.layers.38.self_attn.q_proj", |
|
"model.layers.38.self_attn.k_proj", |
|
"model.layers.38.self_attn.v_proj", |
|
"model.layers.38.self_attn.o_proj", |
|
"model.layers.38.block_sparse_moe.gate", |
|
"model.layers.38.block_sparse_moe.experts.0.w1", |
|
"model.layers.38.block_sparse_moe.experts.0.w2", |
|
"model.layers.38.block_sparse_moe.experts.0.w3", |
|
"model.layers.38.block_sparse_moe.experts.1.w1", |
|
"model.layers.38.block_sparse_moe.experts.1.w2", |
|
"model.layers.38.block_sparse_moe.experts.1.w3", |
|
"model.layers.38.block_sparse_moe.experts.2.w1", |
|
"model.layers.38.block_sparse_moe.experts.2.w2", |
|
"model.layers.38.block_sparse_moe.experts.2.w3", |
|
"model.layers.38.block_sparse_moe.experts.3.w1", |
|
"model.layers.38.block_sparse_moe.experts.3.w2", |
|
"model.layers.38.block_sparse_moe.experts.3.w3", |
|
"model.layers.38.block_sparse_moe.experts.4.w1", |
|
"model.layers.38.block_sparse_moe.experts.4.w2", |
|
"model.layers.38.block_sparse_moe.experts.4.w3", |
|
"model.layers.38.block_sparse_moe.experts.5.w1", |
|
"model.layers.38.block_sparse_moe.experts.5.w2", |
|
"model.layers.38.block_sparse_moe.experts.5.w3", |
|
"model.layers.38.block_sparse_moe.experts.6.w1", |
|
"model.layers.38.block_sparse_moe.experts.6.w2", |
|
"model.layers.38.block_sparse_moe.experts.6.w3", |
|
"model.layers.38.block_sparse_moe.experts.7.w1", |
|
"model.layers.38.block_sparse_moe.experts.7.w2", |
|
"model.layers.38.block_sparse_moe.experts.7.w3", |
|
"model.layers.39.self_attn.q_proj", |
|
"model.layers.39.self_attn.k_proj", |
|
"model.layers.39.self_attn.v_proj", |
|
"model.layers.39.self_attn.o_proj", |
|
"model.layers.39.block_sparse_moe.gate", |
|
"model.layers.39.block_sparse_moe.experts.0.w1", |
|
"model.layers.39.block_sparse_moe.experts.0.w2", |
|
"model.layers.39.block_sparse_moe.experts.0.w3", |
|
"model.layers.39.block_sparse_moe.experts.1.w1", |
|
"model.layers.39.block_sparse_moe.experts.1.w2", |
|
"model.layers.39.block_sparse_moe.experts.1.w3", |
|
"model.layers.39.block_sparse_moe.experts.2.w1", |
|
"model.layers.39.block_sparse_moe.experts.2.w2", |
|
"model.layers.39.block_sparse_moe.experts.2.w3", |
|
"model.layers.39.block_sparse_moe.experts.3.w1", |
|
"model.layers.39.block_sparse_moe.experts.3.w2", |
|
"model.layers.39.block_sparse_moe.experts.3.w3", |
|
"model.layers.39.block_sparse_moe.experts.4.w1", |
|
"model.layers.39.block_sparse_moe.experts.4.w2", |
|
"model.layers.39.block_sparse_moe.experts.4.w3", |
|
"model.layers.39.block_sparse_moe.experts.5.w1", |
|
"model.layers.39.block_sparse_moe.experts.5.w2", |
|
"model.layers.39.block_sparse_moe.experts.5.w3", |
|
"model.layers.39.block_sparse_moe.experts.6.w1", |
|
"model.layers.39.block_sparse_moe.experts.6.w2", |
|
"model.layers.39.block_sparse_moe.experts.6.w3", |
|
"model.layers.39.block_sparse_moe.experts.7.w1", |
|
"model.layers.39.block_sparse_moe.experts.7.w2", |
|
"model.layers.39.block_sparse_moe.experts.7.w3", |
|
"model.layers.40.self_attn.q_proj", |
|
"model.layers.40.self_attn.k_proj", |
|
"model.layers.40.self_attn.v_proj", |
|
"model.layers.40.self_attn.o_proj", |
|
"model.layers.40.block_sparse_moe.gate", |
|
"model.layers.40.block_sparse_moe.experts.0.w1", |
|
"model.layers.40.block_sparse_moe.experts.0.w2", |
|
"model.layers.40.block_sparse_moe.experts.0.w3", |
|
"model.layers.40.block_sparse_moe.experts.1.w1", |
|
"model.layers.40.block_sparse_moe.experts.1.w2", |
|
"model.layers.40.block_sparse_moe.experts.1.w3", |
|
"model.layers.40.block_sparse_moe.experts.2.w1", |
|
"model.layers.40.block_sparse_moe.experts.2.w2", |
|
"model.layers.40.block_sparse_moe.experts.2.w3", |
|
"model.layers.40.block_sparse_moe.experts.3.w1", |
|
"model.layers.40.block_sparse_moe.experts.3.w2", |
|
"model.layers.40.block_sparse_moe.experts.3.w3", |
|
"model.layers.40.block_sparse_moe.experts.4.w1", |
|
"model.layers.40.block_sparse_moe.experts.4.w2", |
|
"model.layers.40.block_sparse_moe.experts.4.w3", |
|
"model.layers.40.block_sparse_moe.experts.5.w1", |
|
"model.layers.40.block_sparse_moe.experts.5.w2", |
|
"model.layers.40.block_sparse_moe.experts.5.w3", |
|
"model.layers.40.block_sparse_moe.experts.6.w1", |
|
"model.layers.40.block_sparse_moe.experts.6.w2", |
|
"model.layers.40.block_sparse_moe.experts.6.w3", |
|
"model.layers.40.block_sparse_moe.experts.7.w1", |
|
"model.layers.40.block_sparse_moe.experts.7.w2", |
|
"model.layers.40.block_sparse_moe.experts.7.w3", |
|
"model.layers.41.self_attn.q_proj", |
|
"model.layers.41.self_attn.k_proj", |
|
"model.layers.41.self_attn.v_proj", |
|
"model.layers.41.self_attn.o_proj", |
|
"model.layers.41.block_sparse_moe.gate", |
|
"model.layers.41.block_sparse_moe.experts.0.w1", |
|
"model.layers.41.block_sparse_moe.experts.0.w2", |
|
"model.layers.41.block_sparse_moe.experts.0.w3", |
|
"model.layers.41.block_sparse_moe.experts.1.w1", |
|
"model.layers.41.block_sparse_moe.experts.1.w2", |
|
"model.layers.41.block_sparse_moe.experts.1.w3", |
|
"model.layers.41.block_sparse_moe.experts.2.w1", |
|
"model.layers.41.block_sparse_moe.experts.2.w2", |
|
"model.layers.41.block_sparse_moe.experts.2.w3", |
|
"model.layers.41.block_sparse_moe.experts.3.w1", |
|
"model.layers.41.block_sparse_moe.experts.3.w2", |
|
"model.layers.41.block_sparse_moe.experts.3.w3", |
|
"model.layers.41.block_sparse_moe.experts.4.w1", |
|
"model.layers.41.block_sparse_moe.experts.4.w2", |
|
"model.layers.41.block_sparse_moe.experts.4.w3", |
|
"model.layers.41.block_sparse_moe.experts.5.w1", |
|
"model.layers.41.block_sparse_moe.experts.5.w2", |
|
"model.layers.41.block_sparse_moe.experts.5.w3", |
|
"model.layers.41.block_sparse_moe.experts.6.w1", |
|
"model.layers.41.block_sparse_moe.experts.6.w2", |
|
"model.layers.41.block_sparse_moe.experts.6.w3", |
|
"model.layers.41.block_sparse_moe.experts.7.w1", |
|
"model.layers.41.block_sparse_moe.experts.7.w2", |
|
"model.layers.41.block_sparse_moe.experts.7.w3", |
|
"model.layers.42.self_attn.q_proj", |
|
"model.layers.42.self_attn.k_proj", |
|
"model.layers.42.self_attn.v_proj", |
|
"model.layers.42.self_attn.o_proj", |
|
"model.layers.42.block_sparse_moe.gate", |
|
"model.layers.42.block_sparse_moe.experts.0.w1", |
|
"model.layers.42.block_sparse_moe.experts.0.w2", |
|
"model.layers.42.block_sparse_moe.experts.0.w3", |
|
"model.layers.42.block_sparse_moe.experts.1.w1", |
|
"model.layers.42.block_sparse_moe.experts.1.w2", |
|
"model.layers.42.block_sparse_moe.experts.1.w3", |
|
"model.layers.42.block_sparse_moe.experts.2.w1", |
|
"model.layers.42.block_sparse_moe.experts.2.w2", |
|
"model.layers.42.block_sparse_moe.experts.2.w3", |
|
"model.layers.42.block_sparse_moe.experts.3.w1", |
|
"model.layers.42.block_sparse_moe.experts.3.w2", |
|
"model.layers.42.block_sparse_moe.experts.3.w3", |
|
"model.layers.42.block_sparse_moe.experts.4.w1", |
|
"model.layers.42.block_sparse_moe.experts.4.w2", |
|
"model.layers.42.block_sparse_moe.experts.4.w3", |
|
"model.layers.42.block_sparse_moe.experts.5.w1", |
|
"model.layers.42.block_sparse_moe.experts.5.w2", |
|
"model.layers.42.block_sparse_moe.experts.5.w3", |
|
"model.layers.42.block_sparse_moe.experts.6.w1", |
|
"model.layers.42.block_sparse_moe.experts.6.w2", |
|
"model.layers.42.block_sparse_moe.experts.6.w3", |
|
"model.layers.42.block_sparse_moe.experts.7.w1", |
|
"model.layers.42.block_sparse_moe.experts.7.w2", |
|
"model.layers.42.block_sparse_moe.experts.7.w3", |
|
"model.layers.43.self_attn.q_proj", |
|
"model.layers.43.self_attn.k_proj", |
|
"model.layers.43.self_attn.v_proj", |
|
"model.layers.43.self_attn.o_proj", |
|
"model.layers.43.block_sparse_moe.gate", |
|
"model.layers.43.block_sparse_moe.experts.0.w1", |
|
"model.layers.43.block_sparse_moe.experts.0.w2", |
|
"model.layers.43.block_sparse_moe.experts.0.w3", |
|
"model.layers.43.block_sparse_moe.experts.1.w1", |
|
"model.layers.43.block_sparse_moe.experts.1.w2", |
|
"model.layers.43.block_sparse_moe.experts.1.w3", |
|
"model.layers.43.block_sparse_moe.experts.2.w1", |
|
"model.layers.43.block_sparse_moe.experts.2.w2", |
|
"model.layers.43.block_sparse_moe.experts.2.w3", |
|
"model.layers.43.block_sparse_moe.experts.3.w1", |
|
"model.layers.43.block_sparse_moe.experts.3.w2", |
|
"model.layers.43.block_sparse_moe.experts.3.w3", |
|
"model.layers.43.block_sparse_moe.experts.4.w1", |
|
"model.layers.43.block_sparse_moe.experts.4.w2", |
|
"model.layers.43.block_sparse_moe.experts.4.w3", |
|
"model.layers.43.block_sparse_moe.experts.5.w1", |
|
"model.layers.43.block_sparse_moe.experts.5.w2", |
|
"model.layers.43.block_sparse_moe.experts.5.w3", |
|
"model.layers.43.block_sparse_moe.experts.6.w1", |
|
"model.layers.43.block_sparse_moe.experts.6.w2", |
|
"model.layers.43.block_sparse_moe.experts.6.w3", |
|
"model.layers.43.block_sparse_moe.experts.7.w1", |
|
"model.layers.43.block_sparse_moe.experts.7.w2", |
|
"model.layers.43.block_sparse_moe.experts.7.w3", |
|
"model.layers.44.self_attn.q_proj", |
|
"model.layers.44.self_attn.k_proj", |
|
"model.layers.44.self_attn.v_proj", |
|
"model.layers.44.self_attn.o_proj", |
|
"model.layers.44.block_sparse_moe.gate", |
|
"model.layers.44.block_sparse_moe.experts.0.w1", |
|
"model.layers.44.block_sparse_moe.experts.0.w2", |
|
"model.layers.44.block_sparse_moe.experts.0.w3", |
|
"model.layers.44.block_sparse_moe.experts.1.w1", |
|
"model.layers.44.block_sparse_moe.experts.1.w2", |
|
"model.layers.44.block_sparse_moe.experts.1.w3", |
|
"model.layers.44.block_sparse_moe.experts.2.w1", |
|
"model.layers.44.block_sparse_moe.experts.2.w2", |
|
"model.layers.44.block_sparse_moe.experts.2.w3", |
|
"model.layers.44.block_sparse_moe.experts.3.w1", |
|
"model.layers.44.block_sparse_moe.experts.3.w2", |
|
"model.layers.44.block_sparse_moe.experts.3.w3", |
|
"model.layers.44.block_sparse_moe.experts.4.w1", |
|
"model.layers.44.block_sparse_moe.experts.4.w2", |
|
"model.layers.44.block_sparse_moe.experts.4.w3", |
|
"model.layers.44.block_sparse_moe.experts.5.w1", |
|
"model.layers.44.block_sparse_moe.experts.5.w2", |
|
"model.layers.44.block_sparse_moe.experts.5.w3", |
|
"model.layers.44.block_sparse_moe.experts.6.w1", |
|
"model.layers.44.block_sparse_moe.experts.6.w2", |
|
"model.layers.44.block_sparse_moe.experts.6.w3", |
|
"model.layers.44.block_sparse_moe.experts.7.w1", |
|
"model.layers.44.block_sparse_moe.experts.7.w2", |
|
"model.layers.44.block_sparse_moe.experts.7.w3", |
|
"model.layers.45.self_attn.q_proj", |
|
"model.layers.45.self_attn.k_proj", |
|
"model.layers.45.self_attn.v_proj", |
|
"model.layers.45.self_attn.o_proj", |
|
"model.layers.45.block_sparse_moe.gate", |
|
"model.layers.45.block_sparse_moe.experts.0.w1", |
|
"model.layers.45.block_sparse_moe.experts.0.w2", |
|
"model.layers.45.block_sparse_moe.experts.0.w3", |
|
"model.layers.45.block_sparse_moe.experts.1.w1", |
|
"model.layers.45.block_sparse_moe.experts.1.w2", |
|
"model.layers.45.block_sparse_moe.experts.1.w3", |
|
"model.layers.45.block_sparse_moe.experts.2.w1", |
|
"model.layers.45.block_sparse_moe.experts.2.w2", |
|
"model.layers.45.block_sparse_moe.experts.2.w3", |
|
"model.layers.45.block_sparse_moe.experts.3.w1", |
|
"model.layers.45.block_sparse_moe.experts.3.w2", |
|
"model.layers.45.block_sparse_moe.experts.3.w3", |
|
"model.layers.45.block_sparse_moe.experts.4.w1", |
|
"model.layers.45.block_sparse_moe.experts.4.w2", |
|
"model.layers.45.block_sparse_moe.experts.4.w3", |
|
"model.layers.45.block_sparse_moe.experts.5.w1", |
|
"model.layers.45.block_sparse_moe.experts.5.w2", |
|
"model.layers.45.block_sparse_moe.experts.5.w3", |
|
"model.layers.45.block_sparse_moe.experts.6.w1", |
|
"model.layers.45.block_sparse_moe.experts.6.w2", |
|
"model.layers.45.block_sparse_moe.experts.6.w3", |
|
"model.layers.45.block_sparse_moe.experts.7.w1", |
|
"model.layers.45.block_sparse_moe.experts.7.w2", |
|
"model.layers.45.block_sparse_moe.experts.7.w3", |
|
"model.layers.46.self_attn.q_proj", |
|
"model.layers.46.self_attn.k_proj", |
|
"model.layers.46.self_attn.v_proj", |
|
"model.layers.46.self_attn.o_proj", |
|
"model.layers.46.block_sparse_moe.gate", |
|
"model.layers.46.block_sparse_moe.experts.0.w1", |
|
"model.layers.46.block_sparse_moe.experts.0.w2", |
|
"model.layers.46.block_sparse_moe.experts.0.w3", |
|
"model.layers.46.block_sparse_moe.experts.1.w1", |
|
"model.layers.46.block_sparse_moe.experts.1.w2", |
|
"model.layers.46.block_sparse_moe.experts.1.w3", |
|
"model.layers.46.block_sparse_moe.experts.2.w1", |
|
"model.layers.46.block_sparse_moe.experts.2.w2", |
|
"model.layers.46.block_sparse_moe.experts.2.w3", |
|
"model.layers.46.block_sparse_moe.experts.3.w1", |
|
"model.layers.46.block_sparse_moe.experts.3.w2", |
|
"model.layers.46.block_sparse_moe.experts.3.w3", |
|
"model.layers.46.block_sparse_moe.experts.4.w1", |
|
"model.layers.46.block_sparse_moe.experts.4.w2", |
|
"model.layers.46.block_sparse_moe.experts.4.w3", |
|
"model.layers.46.block_sparse_moe.experts.5.w1", |
|
"model.layers.46.block_sparse_moe.experts.5.w2", |
|
"model.layers.46.block_sparse_moe.experts.5.w3", |
|
"model.layers.46.block_sparse_moe.experts.6.w1", |
|
"model.layers.46.block_sparse_moe.experts.6.w2", |
|
"model.layers.46.block_sparse_moe.experts.6.w3", |
|
"model.layers.46.block_sparse_moe.experts.7.w1", |
|
"model.layers.46.block_sparse_moe.experts.7.w2", |
|
"model.layers.46.block_sparse_moe.experts.7.w3", |
|
"model.layers.47.self_attn.q_proj", |
|
"model.layers.47.self_attn.k_proj", |
|
"model.layers.47.self_attn.v_proj", |
|
"model.layers.47.self_attn.o_proj", |
|
"model.layers.47.block_sparse_moe.gate", |
|
"model.layers.47.block_sparse_moe.experts.0.w1", |
|
"model.layers.47.block_sparse_moe.experts.0.w2", |
|
"model.layers.47.block_sparse_moe.experts.0.w3", |
|
"model.layers.47.block_sparse_moe.experts.1.w1", |
|
"model.layers.47.block_sparse_moe.experts.1.w2", |
|
"model.layers.47.block_sparse_moe.experts.1.w3", |
|
"model.layers.47.block_sparse_moe.experts.2.w1", |
|
"model.layers.47.block_sparse_moe.experts.2.w2", |
|
"model.layers.47.block_sparse_moe.experts.2.w3", |
|
"model.layers.47.block_sparse_moe.experts.3.w1", |
|
"model.layers.47.block_sparse_moe.experts.3.w2", |
|
"model.layers.47.block_sparse_moe.experts.3.w3", |
|
"model.layers.47.block_sparse_moe.experts.4.w1", |
|
"model.layers.47.block_sparse_moe.experts.4.w2", |
|
"model.layers.47.block_sparse_moe.experts.4.w3", |
|
"model.layers.47.block_sparse_moe.experts.5.w1", |
|
"model.layers.47.block_sparse_moe.experts.5.w2", |
|
"model.layers.47.block_sparse_moe.experts.5.w3", |
|
"model.layers.47.block_sparse_moe.experts.6.w1", |
|
"model.layers.47.block_sparse_moe.experts.6.w2", |
|
"model.layers.47.block_sparse_moe.experts.6.w3", |
|
"model.layers.47.block_sparse_moe.experts.7.w1", |
|
"model.layers.47.block_sparse_moe.experts.7.w2", |
|
"model.layers.47.block_sparse_moe.experts.7.w3", |
|
"model.layers.48.self_attn.q_proj", |
|
"model.layers.48.self_attn.k_proj", |
|
"model.layers.48.self_attn.v_proj", |
|
"model.layers.48.self_attn.o_proj", |
|
"model.layers.48.block_sparse_moe.gate", |
|
"model.layers.48.block_sparse_moe.experts.0.w1", |
|
"model.layers.48.block_sparse_moe.experts.0.w2", |
|
"model.layers.48.block_sparse_moe.experts.0.w3", |
|
"model.layers.48.block_sparse_moe.experts.1.w1", |
|
"model.layers.48.block_sparse_moe.experts.1.w2", |
|
"model.layers.48.block_sparse_moe.experts.1.w3", |
|
"model.layers.48.block_sparse_moe.experts.2.w1", |
|
"model.layers.48.block_sparse_moe.experts.2.w2", |
|
"model.layers.48.block_sparse_moe.experts.2.w3", |
|
"model.layers.48.block_sparse_moe.experts.3.w1", |
|
"model.layers.48.block_sparse_moe.experts.3.w2", |
|
"model.layers.48.block_sparse_moe.experts.3.w3", |
|
"model.layers.48.block_sparse_moe.experts.4.w1", |
|
"model.layers.48.block_sparse_moe.experts.4.w2", |
|
"model.layers.48.block_sparse_moe.experts.4.w3", |
|
"model.layers.48.block_sparse_moe.experts.5.w1", |
|
"model.layers.48.block_sparse_moe.experts.5.w2", |
|
"model.layers.48.block_sparse_moe.experts.5.w3", |
|
"model.layers.48.block_sparse_moe.experts.6.w1", |
|
"model.layers.48.block_sparse_moe.experts.6.w2", |
|
"model.layers.48.block_sparse_moe.experts.6.w3", |
|
"model.layers.48.block_sparse_moe.experts.7.w1", |
|
"model.layers.48.block_sparse_moe.experts.7.w2", |
|
"model.layers.48.block_sparse_moe.experts.7.w3", |
|
"model.layers.49.self_attn.q_proj", |
|
"model.layers.49.self_attn.k_proj", |
|
"model.layers.49.self_attn.v_proj", |
|
"model.layers.49.self_attn.o_proj", |
|
"model.layers.49.block_sparse_moe.gate", |
|
"model.layers.49.block_sparse_moe.experts.0.w1", |
|
"model.layers.49.block_sparse_moe.experts.0.w2", |
|
"model.layers.49.block_sparse_moe.experts.0.w3", |
|
"model.layers.49.block_sparse_moe.experts.1.w1", |
|
"model.layers.49.block_sparse_moe.experts.1.w2", |
|
"model.layers.49.block_sparse_moe.experts.1.w3", |
|
"model.layers.49.block_sparse_moe.experts.2.w1", |
|
"model.layers.49.block_sparse_moe.experts.2.w2", |
|
"model.layers.49.block_sparse_moe.experts.2.w3", |
|
"model.layers.49.block_sparse_moe.experts.3.w1", |
|
"model.layers.49.block_sparse_moe.experts.3.w2", |
|
"model.layers.49.block_sparse_moe.experts.3.w3", |
|
"model.layers.49.block_sparse_moe.experts.4.w1", |
|
"model.layers.49.block_sparse_moe.experts.4.w2", |
|
"model.layers.49.block_sparse_moe.experts.4.w3", |
|
"model.layers.49.block_sparse_moe.experts.5.w1", |
|
"model.layers.49.block_sparse_moe.experts.5.w2", |
|
"model.layers.49.block_sparse_moe.experts.5.w3", |
|
"model.layers.49.block_sparse_moe.experts.6.w1", |
|
"model.layers.49.block_sparse_moe.experts.6.w2", |
|
"model.layers.49.block_sparse_moe.experts.6.w3", |
|
"model.layers.49.block_sparse_moe.experts.7.w1", |
|
"model.layers.49.block_sparse_moe.experts.7.w2", |
|
"model.layers.49.block_sparse_moe.experts.7.w3", |
|
"model.layers.50.self_attn.q_proj", |
|
"model.layers.50.self_attn.k_proj", |
|
"model.layers.50.self_attn.v_proj", |
|
"model.layers.50.self_attn.o_proj", |
|
"model.layers.50.block_sparse_moe.gate", |
|
"model.layers.50.block_sparse_moe.experts.0.w1", |
|
"model.layers.50.block_sparse_moe.experts.0.w2", |
|
"model.layers.50.block_sparse_moe.experts.0.w3", |
|
"model.layers.50.block_sparse_moe.experts.1.w1", |
|
"model.layers.50.block_sparse_moe.experts.1.w2", |
|
"model.layers.50.block_sparse_moe.experts.1.w3", |
|
"model.layers.50.block_sparse_moe.experts.2.w1", |
|
"model.layers.50.block_sparse_moe.experts.2.w2", |
|
"model.layers.50.block_sparse_moe.experts.2.w3", |
|
"model.layers.50.block_sparse_moe.experts.3.w1", |
|
"model.layers.50.block_sparse_moe.experts.3.w2", |
|
"model.layers.50.block_sparse_moe.experts.3.w3", |
|
"model.layers.50.block_sparse_moe.experts.4.w1", |
|
"model.layers.50.block_sparse_moe.experts.4.w2", |
|
"model.layers.50.block_sparse_moe.experts.4.w3", |
|
"model.layers.50.block_sparse_moe.experts.5.w1", |
|
"model.layers.50.block_sparse_moe.experts.5.w2", |
|
"model.layers.50.block_sparse_moe.experts.5.w3", |
|
"model.layers.50.block_sparse_moe.experts.6.w1", |
|
"model.layers.50.block_sparse_moe.experts.6.w2", |
|
"model.layers.50.block_sparse_moe.experts.6.w3", |
|
"model.layers.50.block_sparse_moe.experts.7.w1", |
|
"model.layers.50.block_sparse_moe.experts.7.w2", |
|
"model.layers.50.block_sparse_moe.experts.7.w3", |
|
"model.layers.51.self_attn.q_proj", |
|
"model.layers.51.self_attn.k_proj", |
|
"model.layers.51.self_attn.v_proj", |
|
"model.layers.51.self_attn.o_proj", |
|
"model.layers.51.block_sparse_moe.gate", |
|
"model.layers.51.block_sparse_moe.experts.0.w1", |
|
"model.layers.51.block_sparse_moe.experts.0.w2", |
|
"model.layers.51.block_sparse_moe.experts.0.w3", |
|
"model.layers.51.block_sparse_moe.experts.1.w1", |
|
"model.layers.51.block_sparse_moe.experts.1.w2", |
|
"model.layers.51.block_sparse_moe.experts.1.w3", |
|
"model.layers.51.block_sparse_moe.experts.2.w1", |
|
"model.layers.51.block_sparse_moe.experts.2.w2", |
|
"model.layers.51.block_sparse_moe.experts.2.w3", |
|
"model.layers.51.block_sparse_moe.experts.3.w1", |
|
"model.layers.51.block_sparse_moe.experts.3.w2", |
|
"model.layers.51.block_sparse_moe.experts.3.w3", |
|
"model.layers.51.block_sparse_moe.experts.4.w1", |
|
"model.layers.51.block_sparse_moe.experts.4.w2", |
|
"model.layers.51.block_sparse_moe.experts.4.w3", |
|
"model.layers.51.block_sparse_moe.experts.5.w1", |
|
"model.layers.51.block_sparse_moe.experts.5.w2", |
|
"model.layers.51.block_sparse_moe.experts.5.w3", |
|
"model.layers.51.block_sparse_moe.experts.6.w1", |
|
"model.layers.51.block_sparse_moe.experts.6.w2", |
|
"model.layers.51.block_sparse_moe.experts.6.w3", |
|
"model.layers.51.block_sparse_moe.experts.7.w1", |
|
"model.layers.51.block_sparse_moe.experts.7.w2", |
|
"model.layers.51.block_sparse_moe.experts.7.w3", |
|
"model.layers.52.self_attn.q_proj", |
|
"model.layers.52.self_attn.k_proj", |
|
"model.layers.52.self_attn.v_proj", |
|
"model.layers.52.self_attn.o_proj", |
|
"model.layers.52.block_sparse_moe.gate", |
|
"model.layers.52.block_sparse_moe.experts.0.w1", |
|
"model.layers.52.block_sparse_moe.experts.0.w2", |
|
"model.layers.52.block_sparse_moe.experts.0.w3", |
|
"model.layers.52.block_sparse_moe.experts.1.w1", |
|
"model.layers.52.block_sparse_moe.experts.1.w2", |
|
"model.layers.52.block_sparse_moe.experts.1.w3", |
|
"model.layers.52.block_sparse_moe.experts.2.w1", |
|
"model.layers.52.block_sparse_moe.experts.2.w2", |
|
"model.layers.52.block_sparse_moe.experts.2.w3", |
|
"model.layers.52.block_sparse_moe.experts.3.w1", |
|
"model.layers.52.block_sparse_moe.experts.3.w2", |
|
"model.layers.52.block_sparse_moe.experts.3.w3", |
|
"model.layers.52.block_sparse_moe.experts.4.w1", |
|
"model.layers.52.block_sparse_moe.experts.4.w2", |
|
"model.layers.52.block_sparse_moe.experts.4.w3", |
|
"model.layers.52.block_sparse_moe.experts.5.w1", |
|
"model.layers.52.block_sparse_moe.experts.5.w2", |
|
"model.layers.52.block_sparse_moe.experts.5.w3", |
|
"model.layers.52.block_sparse_moe.experts.6.w1", |
|
"model.layers.52.block_sparse_moe.experts.6.w2", |
|
"model.layers.52.block_sparse_moe.experts.6.w3", |
|
"model.layers.52.block_sparse_moe.experts.7.w1", |
|
"model.layers.52.block_sparse_moe.experts.7.w2", |
|
"model.layers.52.block_sparse_moe.experts.7.w3", |
|
"model.layers.53.self_attn.q_proj", |
|
"model.layers.53.self_attn.k_proj", |
|
"model.layers.53.self_attn.v_proj", |
|
"model.layers.53.self_attn.o_proj", |
|
"model.layers.53.block_sparse_moe.gate", |
|
"model.layers.53.block_sparse_moe.experts.0.w1", |
|
"model.layers.53.block_sparse_moe.experts.0.w2", |
|
"model.layers.53.block_sparse_moe.experts.0.w3", |
|
"model.layers.53.block_sparse_moe.experts.1.w1", |
|
"model.layers.53.block_sparse_moe.experts.1.w2", |
|
"model.layers.53.block_sparse_moe.experts.1.w3", |
|
"model.layers.53.block_sparse_moe.experts.2.w1", |
|
"model.layers.53.block_sparse_moe.experts.2.w2", |
|
"model.layers.53.block_sparse_moe.experts.2.w3", |
|
"model.layers.53.block_sparse_moe.experts.3.w1", |
|
"model.layers.53.block_sparse_moe.experts.3.w2", |
|
"model.layers.53.block_sparse_moe.experts.3.w3", |
|
"model.layers.53.block_sparse_moe.experts.4.w1", |
|
"model.layers.53.block_sparse_moe.experts.4.w2", |
|
"model.layers.53.block_sparse_moe.experts.4.w3", |
|
"model.layers.53.block_sparse_moe.experts.5.w1", |
|
"model.layers.53.block_sparse_moe.experts.5.w2", |
|
"model.layers.53.block_sparse_moe.experts.5.w3", |
|
"model.layers.53.block_sparse_moe.experts.6.w1", |
|
"model.layers.53.block_sparse_moe.experts.6.w2", |
|
"model.layers.53.block_sparse_moe.experts.6.w3", |
|
"model.layers.53.block_sparse_moe.experts.7.w1", |
|
"model.layers.53.block_sparse_moe.experts.7.w2", |
|
"model.layers.53.block_sparse_moe.experts.7.w3", |
|
"model.layers.54.self_attn.q_proj", |
|
"model.layers.54.self_attn.k_proj", |
|
"model.layers.54.self_attn.v_proj", |
|
"model.layers.54.self_attn.o_proj", |
|
"model.layers.54.block_sparse_moe.gate", |
|
"model.layers.54.block_sparse_moe.experts.0.w1", |
|
"model.layers.54.block_sparse_moe.experts.0.w2", |
|
"model.layers.54.block_sparse_moe.experts.0.w3", |
|
"model.layers.54.block_sparse_moe.experts.1.w1", |
|
"model.layers.54.block_sparse_moe.experts.1.w2", |
|
"model.layers.54.block_sparse_moe.experts.1.w3", |
|
"model.layers.54.block_sparse_moe.experts.2.w1", |
|
"model.layers.54.block_sparse_moe.experts.2.w2", |
|
"model.layers.54.block_sparse_moe.experts.2.w3", |
|
"model.layers.54.block_sparse_moe.experts.3.w1", |
|
"model.layers.54.block_sparse_moe.experts.3.w2", |
|
"model.layers.54.block_sparse_moe.experts.3.w3", |
|
"model.layers.54.block_sparse_moe.experts.4.w1", |
|
"model.layers.54.block_sparse_moe.experts.4.w2", |
|
"model.layers.54.block_sparse_moe.experts.4.w3", |
|
"model.layers.54.block_sparse_moe.experts.5.w1", |
|
"model.layers.54.block_sparse_moe.experts.5.w2", |
|
"model.layers.54.block_sparse_moe.experts.5.w3", |
|
"model.layers.54.block_sparse_moe.experts.6.w1", |
|
"model.layers.54.block_sparse_moe.experts.6.w2", |
|
"model.layers.54.block_sparse_moe.experts.6.w3", |
|
"model.layers.54.block_sparse_moe.experts.7.w1", |
|
"model.layers.54.block_sparse_moe.experts.7.w2", |
|
"model.layers.54.block_sparse_moe.experts.7.w3", |
|
"model.layers.55.self_attn.q_proj", |
|
"model.layers.55.self_attn.k_proj", |
|
"model.layers.55.self_attn.v_proj", |
|
"model.layers.55.self_attn.o_proj", |
|
"model.layers.55.block_sparse_moe.gate", |
|
"model.layers.55.block_sparse_moe.experts.0.w1", |
|
"model.layers.55.block_sparse_moe.experts.0.w2", |
|
"model.layers.55.block_sparse_moe.experts.0.w3", |
|
"model.layers.55.block_sparse_moe.experts.1.w1", |
|
"model.layers.55.block_sparse_moe.experts.1.w2", |
|
"model.layers.55.block_sparse_moe.experts.1.w3", |
|
"model.layers.55.block_sparse_moe.experts.2.w1", |
|
"model.layers.55.block_sparse_moe.experts.2.w2", |
|
"model.layers.55.block_sparse_moe.experts.2.w3", |
|
"model.layers.55.block_sparse_moe.experts.3.w1", |
|
"model.layers.55.block_sparse_moe.experts.3.w2", |
|
"model.layers.55.block_sparse_moe.experts.3.w3", |
|
"model.layers.55.block_sparse_moe.experts.4.w1", |
|
"model.layers.55.block_sparse_moe.experts.4.w2", |
|
"model.layers.55.block_sparse_moe.experts.4.w3", |
|
"model.layers.55.block_sparse_moe.experts.5.w1", |
|
"model.layers.55.block_sparse_moe.experts.5.w2", |
|
"model.layers.55.block_sparse_moe.experts.5.w3", |
|
"model.layers.55.block_sparse_moe.experts.6.w1", |
|
"model.layers.55.block_sparse_moe.experts.6.w2", |
|
"model.layers.55.block_sparse_moe.experts.6.w3", |
|
"model.layers.55.block_sparse_moe.experts.7.w1", |
|
"model.layers.55.block_sparse_moe.experts.7.w2", |
|
"model.layers.55.block_sparse_moe.experts.7.w3", |
|
"lm_head" |
|
], |
|
"registry_requires_subclass": false, |
|
"sparsity_structure": "unstructured", |
|
"targets": [ |
|
"model.layers.0.self_attn.q_proj", |
|
"model.layers.0.self_attn.k_proj", |
|
"model.layers.0.self_attn.v_proj", |
|
"model.layers.1.self_attn.q_proj", |
|
"model.layers.1.self_attn.k_proj" |
|
] |
|
} |
|
}, |
|
"rms_norm_eps": 1e-05, |
|
"rope_theta": 1000000, |
|
"router_aux_loss_coef": 0.001, |
|
"router_jitter_noise": 0.0, |
|
"sliding_window": null, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.47.1", |
|
"use_cache": false, |
|
"vocab_size": 32000 |
|
} |