GLM-5-MXFP4 / config.json
jiaxwang's picture
upload model (#1)
4a5ba5f
{
"architectures": [
"GlmMoeDsaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"dtype": "bfloat16",
"eos_token_id": [
154820,
154827,
154829
],
"ep_size": 1,
"first_k_dense_replace": 3,
"hidden_act": "silu",
"head_dim": 64,
"hidden_size": 6144,
"index_head_dim": 128,
"index_n_heads": 32,
"index_topk": 2048,
"indexer_rope_interleave": true,
"initializer_range": 0.02,
"intermediate_size": 12288,
"kv_lora_rank": 512,
"max_position_embeddings": 202752,
"moe_intermediate_size": 2048,
"moe_layer_freq": 1,
"model_type": "glm_moe_dsa",
"n_group": 1,
"n_routed_experts": 256,
"n_shared_experts": 1,
"norm_topk_prob": true,
"num_attention_heads": 64,
"num_experts_per_tok": 8,
"num_hidden_layers": 78,
"num_key_value_heads": 64,
"num_nextn_predict_layers": 1,
"pad_token_id": 154820,
"pretraining_tp": 1,
"q_lora_rank": 2048,
"qk_head_dim": 256,
"qk_nope_head_dim": 192,
"qk_rope_head_dim": 64,
"rms_norm_eps": 1e-05,
"rope_interleave": true,
"rope_parameters": {
"rope_theta": 1000000,
"rope_type": "default"
},
"routed_scaling_factor": 2.5,
"scoring_func": "sigmoid",
"tie_word_embeddings": false,
"topk_group": 1,
"topk_method": "noaux_tc",
"transformers_version": "5.0.2.dev0",
"use_cache": true,
"v_head_dim": 256,
"vocab_size": 154880,
"quantization_config": {
"global_quant_config": {
"input_tensors": {
"dtype": "fp4",
"is_dynamic": true,
"qscheme": "per_group",
"ch_axis": -1,
"group_size": 32,
"symmetric": null,
"round_method": "half_even",
"scale_type": "float",
"scale_format": "e8m0",
"scale_calculation_mode": "even",
"mx_element_dtype": null,
"observer_cls": "PerBlockMXObserver",
"is_scale_quant": false
},
"output_tensors": null,
"weight": {
"dtype": "fp4",
"is_dynamic": false,
"qscheme": "per_group",
"ch_axis": -1,
"group_size": 32,
"symmetric": null,
"round_method": "half_even",
"scale_type": "float",
"scale_format": "e8m0",
"scale_calculation_mode": "even",
"mx_element_dtype": null,
"observer_cls": "PerBlockMXObserver",
"is_scale_quant": false
},
"bias": null,
"target_device": null
},
"exclude": [
"lm_head",
"model.layers.0.mlp.down_proj",
"model.layers.0.mlp.gate_proj",
"model.layers.0.mlp.up_proj",
"model.layers.0.self_attn.indexer.weights_proj",
"model.layers.0.self_attn.indexer.wk",
"model.layers.0.self_attn.indexer.wq_b",
"model.layers.0.self_attn.kv_a_proj_with_mqa",
"model.layers.0.self_attn.kv_b_proj",
"model.layers.0.self_attn.o_proj",
"model.layers.0.self_attn.q_a_proj",
"model.layers.0.self_attn.q_b_proj",
"model.layers.1.mlp.down_proj",
"model.layers.1.mlp.gate_proj",
"model.layers.1.mlp.up_proj",
"model.layers.1.self_attn.indexer.weights_proj",
"model.layers.1.self_attn.indexer.wk",
"model.layers.1.self_attn.indexer.wq_b",
"model.layers.1.self_attn.kv_a_proj_with_mqa",
"model.layers.1.self_attn.kv_b_proj",
"model.layers.1.self_attn.o_proj",
"model.layers.1.self_attn.q_a_proj",
"model.layers.1.self_attn.q_b_proj",
"model.layers.10.mlp.gate",
"model.layers.10.mlp.shared_experts.down_proj",
"model.layers.10.mlp.shared_experts.gate_proj",
"model.layers.10.mlp.shared_experts.up_proj",
"model.layers.10.self_attn.indexer.weights_proj",
"model.layers.10.self_attn.indexer.wk",
"model.layers.10.self_attn.indexer.wq_b",
"model.layers.10.self_attn.kv_a_proj_with_mqa",
"model.layers.10.self_attn.kv_b_proj",
"model.layers.10.self_attn.o_proj",
"model.layers.10.self_attn.q_a_proj",
"model.layers.10.self_attn.q_b_proj",
"model.layers.11.mlp.gate",
"model.layers.11.mlp.shared_experts.down_proj",
"model.layers.11.mlp.shared_experts.gate_proj",
"model.layers.11.mlp.shared_experts.up_proj",
"model.layers.11.self_attn.indexer.weights_proj",
"model.layers.11.self_attn.indexer.wk",
"model.layers.11.self_attn.indexer.wq_b",
"model.layers.11.self_attn.kv_a_proj_with_mqa",
"model.layers.11.self_attn.kv_b_proj",
"model.layers.11.self_attn.o_proj",
"model.layers.11.self_attn.q_a_proj",
"model.layers.11.self_attn.q_b_proj",
"model.layers.12.mlp.gate",
"model.layers.12.mlp.shared_experts.down_proj",
"model.layers.12.mlp.shared_experts.gate_proj",
"model.layers.12.mlp.shared_experts.up_proj",
"model.layers.12.self_attn.indexer.weights_proj",
"model.layers.12.self_attn.indexer.wk",
"model.layers.12.self_attn.indexer.wq_b",
"model.layers.12.self_attn.kv_a_proj_with_mqa",
"model.layers.12.self_attn.kv_b_proj",
"model.layers.12.self_attn.o_proj",
"model.layers.12.self_attn.q_a_proj",
"model.layers.12.self_attn.q_b_proj",
"model.layers.13.mlp.gate",
"model.layers.13.mlp.shared_experts.down_proj",
"model.layers.13.mlp.shared_experts.gate_proj",
"model.layers.13.mlp.shared_experts.up_proj",
"model.layers.13.self_attn.indexer.weights_proj",
"model.layers.13.self_attn.indexer.wk",
"model.layers.13.self_attn.indexer.wq_b",
"model.layers.13.self_attn.kv_a_proj_with_mqa",
"model.layers.13.self_attn.kv_b_proj",
"model.layers.13.self_attn.o_proj",
"model.layers.13.self_attn.q_a_proj",
"model.layers.13.self_attn.q_b_proj",
"model.layers.14.mlp.gate",
"model.layers.14.mlp.shared_experts.down_proj",
"model.layers.14.mlp.shared_experts.gate_proj",
"model.layers.14.mlp.shared_experts.up_proj",
"model.layers.14.self_attn.indexer.weights_proj",
"model.layers.14.self_attn.indexer.wk",
"model.layers.14.self_attn.indexer.wq_b",
"model.layers.14.self_attn.kv_a_proj_with_mqa",
"model.layers.14.self_attn.kv_b_proj",
"model.layers.14.self_attn.o_proj",
"model.layers.14.self_attn.q_a_proj",
"model.layers.14.self_attn.q_b_proj",
"model.layers.15.mlp.gate",
"model.layers.15.mlp.shared_experts.down_proj",
"model.layers.15.mlp.shared_experts.gate_proj",
"model.layers.15.mlp.shared_experts.up_proj",
"model.layers.15.self_attn.indexer.weights_proj",
"model.layers.15.self_attn.indexer.wk",
"model.layers.15.self_attn.indexer.wq_b",
"model.layers.15.self_attn.kv_a_proj_with_mqa",
"model.layers.15.self_attn.kv_b_proj",
"model.layers.15.self_attn.o_proj",
"model.layers.15.self_attn.q_a_proj",
"model.layers.15.self_attn.q_b_proj",
"model.layers.16.mlp.gate",
"model.layers.16.mlp.shared_experts.down_proj",
"model.layers.16.mlp.shared_experts.gate_proj",
"model.layers.16.mlp.shared_experts.up_proj",
"model.layers.16.self_attn.indexer.weights_proj",
"model.layers.16.self_attn.indexer.wk",
"model.layers.16.self_attn.indexer.wq_b",
"model.layers.16.self_attn.kv_a_proj_with_mqa",
"model.layers.16.self_attn.kv_b_proj",
"model.layers.16.self_attn.o_proj",
"model.layers.16.self_attn.q_a_proj",
"model.layers.16.self_attn.q_b_proj",
"model.layers.17.mlp.gate",
"model.layers.17.mlp.shared_experts.down_proj",
"model.layers.17.mlp.shared_experts.gate_proj",
"model.layers.17.mlp.shared_experts.up_proj",
"model.layers.17.self_attn.indexer.weights_proj",
"model.layers.17.self_attn.indexer.wk",
"model.layers.17.self_attn.indexer.wq_b",
"model.layers.17.self_attn.kv_a_proj_with_mqa",
"model.layers.17.self_attn.kv_b_proj",
"model.layers.17.self_attn.o_proj",
"model.layers.17.self_attn.q_a_proj",
"model.layers.17.self_attn.q_b_proj",
"model.layers.18.mlp.gate",
"model.layers.18.mlp.shared_experts.down_proj",
"model.layers.18.mlp.shared_experts.gate_proj",
"model.layers.18.mlp.shared_experts.up_proj",
"model.layers.18.self_attn.indexer.weights_proj",
"model.layers.18.self_attn.indexer.wk",
"model.layers.18.self_attn.indexer.wq_b",
"model.layers.18.self_attn.kv_a_proj_with_mqa",
"model.layers.18.self_attn.kv_b_proj",
"model.layers.18.self_attn.o_proj",
"model.layers.18.self_attn.q_a_proj",
"model.layers.18.self_attn.q_b_proj",
"model.layers.19.mlp.gate",
"model.layers.19.mlp.shared_experts.down_proj",
"model.layers.19.mlp.shared_experts.gate_proj",
"model.layers.19.mlp.shared_experts.up_proj",
"model.layers.19.self_attn.indexer.weights_proj",
"model.layers.19.self_attn.indexer.wk",
"model.layers.19.self_attn.indexer.wq_b",
"model.layers.19.self_attn.kv_a_proj_with_mqa",
"model.layers.19.self_attn.kv_b_proj",
"model.layers.19.self_attn.o_proj",
"model.layers.19.self_attn.q_a_proj",
"model.layers.19.self_attn.q_b_proj",
"model.layers.2.mlp.down_proj",
"model.layers.2.mlp.gate_proj",
"model.layers.2.mlp.up_proj",
"model.layers.2.self_attn.indexer.weights_proj",
"model.layers.2.self_attn.indexer.wk",
"model.layers.2.self_attn.indexer.wq_b",
"model.layers.2.self_attn.kv_a_proj_with_mqa",
"model.layers.2.self_attn.kv_b_proj",
"model.layers.2.self_attn.o_proj",
"model.layers.2.self_attn.q_a_proj",
"model.layers.2.self_attn.q_b_proj",
"model.layers.20.mlp.gate",
"model.layers.20.mlp.shared_experts.down_proj",
"model.layers.20.mlp.shared_experts.gate_proj",
"model.layers.20.mlp.shared_experts.up_proj",
"model.layers.20.self_attn.indexer.weights_proj",
"model.layers.20.self_attn.indexer.wk",
"model.layers.20.self_attn.indexer.wq_b",
"model.layers.20.self_attn.kv_a_proj_with_mqa",
"model.layers.20.self_attn.kv_b_proj",
"model.layers.20.self_attn.o_proj",
"model.layers.20.self_attn.q_a_proj",
"model.layers.20.self_attn.q_b_proj",
"model.layers.21.mlp.gate",
"model.layers.21.mlp.shared_experts.down_proj",
"model.layers.21.mlp.shared_experts.gate_proj",
"model.layers.21.mlp.shared_experts.up_proj",
"model.layers.21.self_attn.indexer.weights_proj",
"model.layers.21.self_attn.indexer.wk",
"model.layers.21.self_attn.indexer.wq_b",
"model.layers.21.self_attn.kv_a_proj_with_mqa",
"model.layers.21.self_attn.kv_b_proj",
"model.layers.21.self_attn.o_proj",
"model.layers.21.self_attn.q_a_proj",
"model.layers.21.self_attn.q_b_proj",
"model.layers.22.mlp.gate",
"model.layers.22.mlp.shared_experts.down_proj",
"model.layers.22.mlp.shared_experts.gate_proj",
"model.layers.22.mlp.shared_experts.up_proj",
"model.layers.22.self_attn.indexer.weights_proj",
"model.layers.22.self_attn.indexer.wk",
"model.layers.22.self_attn.indexer.wq_b",
"model.layers.22.self_attn.kv_a_proj_with_mqa",
"model.layers.22.self_attn.kv_b_proj",
"model.layers.22.self_attn.o_proj",
"model.layers.22.self_attn.q_a_proj",
"model.layers.22.self_attn.q_b_proj",
"model.layers.23.mlp.gate",
"model.layers.23.mlp.shared_experts.down_proj",
"model.layers.23.mlp.shared_experts.gate_proj",
"model.layers.23.mlp.shared_experts.up_proj",
"model.layers.23.self_attn.indexer.weights_proj",
"model.layers.23.self_attn.indexer.wk",
"model.layers.23.self_attn.indexer.wq_b",
"model.layers.23.self_attn.kv_a_proj_with_mqa",
"model.layers.23.self_attn.kv_b_proj",
"model.layers.23.self_attn.o_proj",
"model.layers.23.self_attn.q_a_proj",
"model.layers.23.self_attn.q_b_proj",
"model.layers.24.mlp.gate",
"model.layers.24.mlp.shared_experts.down_proj",
"model.layers.24.mlp.shared_experts.gate_proj",
"model.layers.24.mlp.shared_experts.up_proj",
"model.layers.24.self_attn.indexer.weights_proj",
"model.layers.24.self_attn.indexer.wk",
"model.layers.24.self_attn.indexer.wq_b",
"model.layers.24.self_attn.kv_a_proj_with_mqa",
"model.layers.24.self_attn.kv_b_proj",
"model.layers.24.self_attn.o_proj",
"model.layers.24.self_attn.q_a_proj",
"model.layers.24.self_attn.q_b_proj",
"model.layers.25.mlp.gate",
"model.layers.25.mlp.shared_experts.down_proj",
"model.layers.25.mlp.shared_experts.gate_proj",
"model.layers.25.mlp.shared_experts.up_proj",
"model.layers.25.self_attn.indexer.weights_proj",
"model.layers.25.self_attn.indexer.wk",
"model.layers.25.self_attn.indexer.wq_b",
"model.layers.25.self_attn.kv_a_proj_with_mqa",
"model.layers.25.self_attn.kv_b_proj",
"model.layers.25.self_attn.o_proj",
"model.layers.25.self_attn.q_a_proj",
"model.layers.25.self_attn.q_b_proj",
"model.layers.26.mlp.gate",
"model.layers.26.mlp.shared_experts.down_proj",
"model.layers.26.mlp.shared_experts.gate_proj",
"model.layers.26.mlp.shared_experts.up_proj",
"model.layers.26.self_attn.indexer.weights_proj",
"model.layers.26.self_attn.indexer.wk",
"model.layers.26.self_attn.indexer.wq_b",
"model.layers.26.self_attn.kv_a_proj_with_mqa",
"model.layers.26.self_attn.kv_b_proj",
"model.layers.26.self_attn.o_proj",
"model.layers.26.self_attn.q_a_proj",
"model.layers.26.self_attn.q_b_proj",
"model.layers.27.mlp.gate",
"model.layers.27.mlp.shared_experts.down_proj",
"model.layers.27.mlp.shared_experts.gate_proj",
"model.layers.27.mlp.shared_experts.up_proj",
"model.layers.27.self_attn.indexer.weights_proj",
"model.layers.27.self_attn.indexer.wk",
"model.layers.27.self_attn.indexer.wq_b",
"model.layers.27.self_attn.kv_a_proj_with_mqa",
"model.layers.27.self_attn.kv_b_proj",
"model.layers.27.self_attn.o_proj",
"model.layers.27.self_attn.q_a_proj",
"model.layers.27.self_attn.q_b_proj",
"model.layers.28.mlp.gate",
"model.layers.28.mlp.shared_experts.down_proj",
"model.layers.28.mlp.shared_experts.gate_proj",
"model.layers.28.mlp.shared_experts.up_proj",
"model.layers.28.self_attn.indexer.weights_proj",
"model.layers.28.self_attn.indexer.wk",
"model.layers.28.self_attn.indexer.wq_b",
"model.layers.28.self_attn.kv_a_proj_with_mqa",
"model.layers.28.self_attn.kv_b_proj",
"model.layers.28.self_attn.o_proj",
"model.layers.28.self_attn.q_a_proj",
"model.layers.28.self_attn.q_b_proj",
"model.layers.29.mlp.gate",
"model.layers.29.mlp.shared_experts.down_proj",
"model.layers.29.mlp.shared_experts.gate_proj",
"model.layers.29.mlp.shared_experts.up_proj",
"model.layers.29.self_attn.indexer.weights_proj",
"model.layers.29.self_attn.indexer.wk",
"model.layers.29.self_attn.indexer.wq_b",
"model.layers.29.self_attn.kv_a_proj_with_mqa",
"model.layers.29.self_attn.kv_b_proj",
"model.layers.29.self_attn.o_proj",
"model.layers.29.self_attn.q_a_proj",
"model.layers.29.self_attn.q_b_proj",
"model.layers.3.mlp.gate",
"model.layers.3.mlp.shared_experts.down_proj",
"model.layers.3.mlp.shared_experts.gate_proj",
"model.layers.3.mlp.shared_experts.up_proj",
"model.layers.3.self_attn.indexer.weights_proj",
"model.layers.3.self_attn.indexer.wk",
"model.layers.3.self_attn.indexer.wq_b",
"model.layers.3.self_attn.kv_a_proj_with_mqa",
"model.layers.3.self_attn.kv_b_proj",
"model.layers.3.self_attn.o_proj",
"model.layers.3.self_attn.q_a_proj",
"model.layers.3.self_attn.q_b_proj",
"model.layers.30.mlp.gate",
"model.layers.30.mlp.shared_experts.down_proj",
"model.layers.30.mlp.shared_experts.gate_proj",
"model.layers.30.mlp.shared_experts.up_proj",
"model.layers.30.self_attn.indexer.weights_proj",
"model.layers.30.self_attn.indexer.wk",
"model.layers.30.self_attn.indexer.wq_b",
"model.layers.30.self_attn.kv_a_proj_with_mqa",
"model.layers.30.self_attn.kv_b_proj",
"model.layers.30.self_attn.o_proj",
"model.layers.30.self_attn.q_a_proj",
"model.layers.30.self_attn.q_b_proj",
"model.layers.31.mlp.gate",
"model.layers.31.mlp.shared_experts.down_proj",
"model.layers.31.mlp.shared_experts.gate_proj",
"model.layers.31.mlp.shared_experts.up_proj",
"model.layers.31.self_attn.indexer.weights_proj",
"model.layers.31.self_attn.indexer.wk",
"model.layers.31.self_attn.indexer.wq_b",
"model.layers.31.self_attn.kv_a_proj_with_mqa",
"model.layers.31.self_attn.kv_b_proj",
"model.layers.31.self_attn.o_proj",
"model.layers.31.self_attn.q_a_proj",
"model.layers.31.self_attn.q_b_proj",
"model.layers.32.mlp.gate",
"model.layers.32.mlp.shared_experts.down_proj",
"model.layers.32.mlp.shared_experts.gate_proj",
"model.layers.32.mlp.shared_experts.up_proj",
"model.layers.32.self_attn.indexer.weights_proj",
"model.layers.32.self_attn.indexer.wk",
"model.layers.32.self_attn.indexer.wq_b",
"model.layers.32.self_attn.kv_a_proj_with_mqa",
"model.layers.32.self_attn.kv_b_proj",
"model.layers.32.self_attn.o_proj",
"model.layers.32.self_attn.q_a_proj",
"model.layers.32.self_attn.q_b_proj",
"model.layers.33.mlp.gate",
"model.layers.33.mlp.shared_experts.down_proj",
"model.layers.33.mlp.shared_experts.gate_proj",
"model.layers.33.mlp.shared_experts.up_proj",
"model.layers.33.self_attn.indexer.weights_proj",
"model.layers.33.self_attn.indexer.wk",
"model.layers.33.self_attn.indexer.wq_b",
"model.layers.33.self_attn.kv_a_proj_with_mqa",
"model.layers.33.self_attn.kv_b_proj",
"model.layers.33.self_attn.o_proj",
"model.layers.33.self_attn.q_a_proj",
"model.layers.33.self_attn.q_b_proj",
"model.layers.34.mlp.gate",
"model.layers.34.mlp.shared_experts.down_proj",
"model.layers.34.mlp.shared_experts.gate_proj",
"model.layers.34.mlp.shared_experts.up_proj",
"model.layers.34.self_attn.indexer.weights_proj",
"model.layers.34.self_attn.indexer.wk",
"model.layers.34.self_attn.indexer.wq_b",
"model.layers.34.self_attn.kv_a_proj_with_mqa",
"model.layers.34.self_attn.kv_b_proj",
"model.layers.34.self_attn.o_proj",
"model.layers.34.self_attn.q_a_proj",
"model.layers.34.self_attn.q_b_proj",
"model.layers.35.mlp.gate",
"model.layers.35.mlp.shared_experts.down_proj",
"model.layers.35.mlp.shared_experts.gate_proj",
"model.layers.35.mlp.shared_experts.up_proj",
"model.layers.35.self_attn.indexer.weights_proj",
"model.layers.35.self_attn.indexer.wk",
"model.layers.35.self_attn.indexer.wq_b",
"model.layers.35.self_attn.kv_a_proj_with_mqa",
"model.layers.35.self_attn.kv_b_proj",
"model.layers.35.self_attn.o_proj",
"model.layers.35.self_attn.q_a_proj",
"model.layers.35.self_attn.q_b_proj",
"model.layers.36.mlp.gate",
"model.layers.36.mlp.shared_experts.down_proj",
"model.layers.36.mlp.shared_experts.gate_proj",
"model.layers.36.mlp.shared_experts.up_proj",
"model.layers.36.self_attn.indexer.weights_proj",
"model.layers.36.self_attn.indexer.wk",
"model.layers.36.self_attn.indexer.wq_b",
"model.layers.36.self_attn.kv_a_proj_with_mqa",
"model.layers.36.self_attn.kv_b_proj",
"model.layers.36.self_attn.o_proj",
"model.layers.36.self_attn.q_a_proj",
"model.layers.36.self_attn.q_b_proj",
"model.layers.37.mlp.gate",
"model.layers.37.mlp.shared_experts.down_proj",
"model.layers.37.mlp.shared_experts.gate_proj",
"model.layers.37.mlp.shared_experts.up_proj",
"model.layers.37.self_attn.indexer.weights_proj",
"model.layers.37.self_attn.indexer.wk",
"model.layers.37.self_attn.indexer.wq_b",
"model.layers.37.self_attn.kv_a_proj_with_mqa",
"model.layers.37.self_attn.kv_b_proj",
"model.layers.37.self_attn.o_proj",
"model.layers.37.self_attn.q_a_proj",
"model.layers.37.self_attn.q_b_proj",
"model.layers.38.mlp.gate",
"model.layers.38.mlp.shared_experts.down_proj",
"model.layers.38.mlp.shared_experts.gate_proj",
"model.layers.38.mlp.shared_experts.up_proj",
"model.layers.38.self_attn.indexer.weights_proj",
"model.layers.38.self_attn.indexer.wk",
"model.layers.38.self_attn.indexer.wq_b",
"model.layers.38.self_attn.kv_a_proj_with_mqa",
"model.layers.38.self_attn.kv_b_proj",
"model.layers.38.self_attn.o_proj",
"model.layers.38.self_attn.q_a_proj",
"model.layers.38.self_attn.q_b_proj",
"model.layers.39.mlp.gate",
"model.layers.39.mlp.shared_experts.down_proj",
"model.layers.39.mlp.shared_experts.gate_proj",
"model.layers.39.mlp.shared_experts.up_proj",
"model.layers.39.self_attn.indexer.weights_proj",
"model.layers.39.self_attn.indexer.wk",
"model.layers.39.self_attn.indexer.wq_b",
"model.layers.39.self_attn.kv_a_proj_with_mqa",
"model.layers.39.self_attn.kv_b_proj",
"model.layers.39.self_attn.o_proj",
"model.layers.39.self_attn.q_a_proj",
"model.layers.39.self_attn.q_b_proj",
"model.layers.4.mlp.gate",
"model.layers.4.mlp.shared_experts.down_proj",
"model.layers.4.mlp.shared_experts.gate_proj",
"model.layers.4.mlp.shared_experts.up_proj",
"model.layers.4.self_attn.indexer.weights_proj",
"model.layers.4.self_attn.indexer.wk",
"model.layers.4.self_attn.indexer.wq_b",
"model.layers.4.self_attn.kv_a_proj_with_mqa",
"model.layers.4.self_attn.kv_b_proj",
"model.layers.4.self_attn.o_proj",
"model.layers.4.self_attn.q_a_proj",
"model.layers.4.self_attn.q_b_proj",
"model.layers.40.mlp.gate",
"model.layers.40.mlp.shared_experts.down_proj",
"model.layers.40.mlp.shared_experts.gate_proj",
"model.layers.40.mlp.shared_experts.up_proj",
"model.layers.40.self_attn.indexer.weights_proj",
"model.layers.40.self_attn.indexer.wk",
"model.layers.40.self_attn.indexer.wq_b",
"model.layers.40.self_attn.kv_a_proj_with_mqa",
"model.layers.40.self_attn.kv_b_proj",
"model.layers.40.self_attn.o_proj",
"model.layers.40.self_attn.q_a_proj",
"model.layers.40.self_attn.q_b_proj",
"model.layers.41.mlp.gate",
"model.layers.41.mlp.shared_experts.down_proj",
"model.layers.41.mlp.shared_experts.gate_proj",
"model.layers.41.mlp.shared_experts.up_proj",
"model.layers.41.self_attn.indexer.weights_proj",
"model.layers.41.self_attn.indexer.wk",
"model.layers.41.self_attn.indexer.wq_b",
"model.layers.41.self_attn.kv_a_proj_with_mqa",
"model.layers.41.self_attn.kv_b_proj",
"model.layers.41.self_attn.o_proj",
"model.layers.41.self_attn.q_a_proj",
"model.layers.41.self_attn.q_b_proj",
"model.layers.42.mlp.gate",
"model.layers.42.mlp.shared_experts.down_proj",
"model.layers.42.mlp.shared_experts.gate_proj",
"model.layers.42.mlp.shared_experts.up_proj",
"model.layers.42.self_attn.indexer.weights_proj",
"model.layers.42.self_attn.indexer.wk",
"model.layers.42.self_attn.indexer.wq_b",
"model.layers.42.self_attn.kv_a_proj_with_mqa",
"model.layers.42.self_attn.kv_b_proj",
"model.layers.42.self_attn.o_proj",
"model.layers.42.self_attn.q_a_proj",
"model.layers.42.self_attn.q_b_proj",
"model.layers.43.mlp.gate",
"model.layers.43.mlp.shared_experts.down_proj",
"model.layers.43.mlp.shared_experts.gate_proj",
"model.layers.43.mlp.shared_experts.up_proj",
"model.layers.43.self_attn.indexer.weights_proj",
"model.layers.43.self_attn.indexer.wk",
"model.layers.43.self_attn.indexer.wq_b",
"model.layers.43.self_attn.kv_a_proj_with_mqa",
"model.layers.43.self_attn.kv_b_proj",
"model.layers.43.self_attn.o_proj",
"model.layers.43.self_attn.q_a_proj",
"model.layers.43.self_attn.q_b_proj",
"model.layers.44.mlp.gate",
"model.layers.44.mlp.shared_experts.down_proj",
"model.layers.44.mlp.shared_experts.gate_proj",
"model.layers.44.mlp.shared_experts.up_proj",
"model.layers.44.self_attn.indexer.weights_proj",
"model.layers.44.self_attn.indexer.wk",
"model.layers.44.self_attn.indexer.wq_b",
"model.layers.44.self_attn.kv_a_proj_with_mqa",
"model.layers.44.self_attn.kv_b_proj",
"model.layers.44.self_attn.o_proj",
"model.layers.44.self_attn.q_a_proj",
"model.layers.44.self_attn.q_b_proj",
"model.layers.45.mlp.gate",
"model.layers.45.mlp.shared_experts.down_proj",
"model.layers.45.mlp.shared_experts.gate_proj",
"model.layers.45.mlp.shared_experts.up_proj",
"model.layers.45.self_attn.indexer.weights_proj",
"model.layers.45.self_attn.indexer.wk",
"model.layers.45.self_attn.indexer.wq_b",
"model.layers.45.self_attn.kv_a_proj_with_mqa",
"model.layers.45.self_attn.kv_b_proj",
"model.layers.45.self_attn.o_proj",
"model.layers.45.self_attn.q_a_proj",
"model.layers.45.self_attn.q_b_proj",
"model.layers.46.mlp.gate",
"model.layers.46.mlp.shared_experts.down_proj",
"model.layers.46.mlp.shared_experts.gate_proj",
"model.layers.46.mlp.shared_experts.up_proj",
"model.layers.46.self_attn.indexer.weights_proj",
"model.layers.46.self_attn.indexer.wk",
"model.layers.46.self_attn.indexer.wq_b",
"model.layers.46.self_attn.kv_a_proj_with_mqa",
"model.layers.46.self_attn.kv_b_proj",
"model.layers.46.self_attn.o_proj",
"model.layers.46.self_attn.q_a_proj",
"model.layers.46.self_attn.q_b_proj",
"model.layers.47.mlp.gate",
"model.layers.47.mlp.shared_experts.down_proj",
"model.layers.47.mlp.shared_experts.gate_proj",
"model.layers.47.mlp.shared_experts.up_proj",
"model.layers.47.self_attn.indexer.weights_proj",
"model.layers.47.self_attn.indexer.wk",
"model.layers.47.self_attn.indexer.wq_b",
"model.layers.47.self_attn.kv_a_proj_with_mqa",
"model.layers.47.self_attn.kv_b_proj",
"model.layers.47.self_attn.o_proj",
"model.layers.47.self_attn.q_a_proj",
"model.layers.47.self_attn.q_b_proj",
"model.layers.48.mlp.gate",
"model.layers.48.mlp.shared_experts.down_proj",
"model.layers.48.mlp.shared_experts.gate_proj",
"model.layers.48.mlp.shared_experts.up_proj",
"model.layers.48.self_attn.indexer.weights_proj",
"model.layers.48.self_attn.indexer.wk",
"model.layers.48.self_attn.indexer.wq_b",
"model.layers.48.self_attn.kv_a_proj_with_mqa",
"model.layers.48.self_attn.kv_b_proj",
"model.layers.48.self_attn.o_proj",
"model.layers.48.self_attn.q_a_proj",
"model.layers.48.self_attn.q_b_proj",
"model.layers.49.mlp.gate",
"model.layers.49.mlp.shared_experts.down_proj",
"model.layers.49.mlp.shared_experts.gate_proj",
"model.layers.49.mlp.shared_experts.up_proj",
"model.layers.49.self_attn.indexer.weights_proj",
"model.layers.49.self_attn.indexer.wk",
"model.layers.49.self_attn.indexer.wq_b",
"model.layers.49.self_attn.kv_a_proj_with_mqa",
"model.layers.49.self_attn.kv_b_proj",
"model.layers.49.self_attn.o_proj",
"model.layers.49.self_attn.q_a_proj",
"model.layers.49.self_attn.q_b_proj",
"model.layers.5.mlp.gate",
"model.layers.5.mlp.shared_experts.down_proj",
"model.layers.5.mlp.shared_experts.gate_proj",
"model.layers.5.mlp.shared_experts.up_proj",
"model.layers.5.self_attn.indexer.weights_proj",
"model.layers.5.self_attn.indexer.wk",
"model.layers.5.self_attn.indexer.wq_b",
"model.layers.5.self_attn.kv_a_proj_with_mqa",
"model.layers.5.self_attn.kv_b_proj",
"model.layers.5.self_attn.o_proj",
"model.layers.5.self_attn.q_a_proj",
"model.layers.5.self_attn.q_b_proj",
"model.layers.50.mlp.gate",
"model.layers.50.mlp.shared_experts.down_proj",
"model.layers.50.mlp.shared_experts.gate_proj",
"model.layers.50.mlp.shared_experts.up_proj",
"model.layers.50.self_attn.indexer.weights_proj",
"model.layers.50.self_attn.indexer.wk",
"model.layers.50.self_attn.indexer.wq_b",
"model.layers.50.self_attn.kv_a_proj_with_mqa",
"model.layers.50.self_attn.kv_b_proj",
"model.layers.50.self_attn.o_proj",
"model.layers.50.self_attn.q_a_proj",
"model.layers.50.self_attn.q_b_proj",
"model.layers.51.mlp.gate",
"model.layers.51.mlp.shared_experts.down_proj",
"model.layers.51.mlp.shared_experts.gate_proj",
"model.layers.51.mlp.shared_experts.up_proj",
"model.layers.51.self_attn.indexer.weights_proj",
"model.layers.51.self_attn.indexer.wk",
"model.layers.51.self_attn.indexer.wq_b",
"model.layers.51.self_attn.kv_a_proj_with_mqa",
"model.layers.51.self_attn.kv_b_proj",
"model.layers.51.self_attn.o_proj",
"model.layers.51.self_attn.q_a_proj",
"model.layers.51.self_attn.q_b_proj",
"model.layers.52.mlp.gate",
"model.layers.52.mlp.shared_experts.down_proj",
"model.layers.52.mlp.shared_experts.gate_proj",
"model.layers.52.mlp.shared_experts.up_proj",
"model.layers.52.self_attn.indexer.weights_proj",
"model.layers.52.self_attn.indexer.wk",
"model.layers.52.self_attn.indexer.wq_b",
"model.layers.52.self_attn.kv_a_proj_with_mqa",
"model.layers.52.self_attn.kv_b_proj",
"model.layers.52.self_attn.o_proj",
"model.layers.52.self_attn.q_a_proj",
"model.layers.52.self_attn.q_b_proj",
"model.layers.53.mlp.gate",
"model.layers.53.mlp.shared_experts.down_proj",
"model.layers.53.mlp.shared_experts.gate_proj",
"model.layers.53.mlp.shared_experts.up_proj",
"model.layers.53.self_attn.indexer.weights_proj",
"model.layers.53.self_attn.indexer.wk",
"model.layers.53.self_attn.indexer.wq_b",
"model.layers.53.self_attn.kv_a_proj_with_mqa",
"model.layers.53.self_attn.kv_b_proj",
"model.layers.53.self_attn.o_proj",
"model.layers.53.self_attn.q_a_proj",
"model.layers.53.self_attn.q_b_proj",
"model.layers.54.mlp.gate",
"model.layers.54.mlp.shared_experts.down_proj",
"model.layers.54.mlp.shared_experts.gate_proj",
"model.layers.54.mlp.shared_experts.up_proj",
"model.layers.54.self_attn.indexer.weights_proj",
"model.layers.54.self_attn.indexer.wk",
"model.layers.54.self_attn.indexer.wq_b",
"model.layers.54.self_attn.kv_a_proj_with_mqa",
"model.layers.54.self_attn.kv_b_proj",
"model.layers.54.self_attn.o_proj",
"model.layers.54.self_attn.q_a_proj",
"model.layers.54.self_attn.q_b_proj",
"model.layers.55.mlp.gate",
"model.layers.55.mlp.shared_experts.down_proj",
"model.layers.55.mlp.shared_experts.gate_proj",
"model.layers.55.mlp.shared_experts.up_proj",
"model.layers.55.self_attn.indexer.weights_proj",
"model.layers.55.self_attn.indexer.wk",
"model.layers.55.self_attn.indexer.wq_b",
"model.layers.55.self_attn.kv_a_proj_with_mqa",
"model.layers.55.self_attn.kv_b_proj",
"model.layers.55.self_attn.o_proj",
"model.layers.55.self_attn.q_a_proj",
"model.layers.55.self_attn.q_b_proj",
"model.layers.56.mlp.gate",
"model.layers.56.mlp.shared_experts.down_proj",
"model.layers.56.mlp.shared_experts.gate_proj",
"model.layers.56.mlp.shared_experts.up_proj",
"model.layers.56.self_attn.indexer.weights_proj",
"model.layers.56.self_attn.indexer.wk",
"model.layers.56.self_attn.indexer.wq_b",
"model.layers.56.self_attn.kv_a_proj_with_mqa",
"model.layers.56.self_attn.kv_b_proj",
"model.layers.56.self_attn.o_proj",
"model.layers.56.self_attn.q_a_proj",
"model.layers.56.self_attn.q_b_proj",
"model.layers.57.mlp.gate",
"model.layers.57.mlp.shared_experts.down_proj",
"model.layers.57.mlp.shared_experts.gate_proj",
"model.layers.57.mlp.shared_experts.up_proj",
"model.layers.57.self_attn.indexer.weights_proj",
"model.layers.57.self_attn.indexer.wk",
"model.layers.57.self_attn.indexer.wq_b",
"model.layers.57.self_attn.kv_a_proj_with_mqa",
"model.layers.57.self_attn.kv_b_proj",
"model.layers.57.self_attn.o_proj",
"model.layers.57.self_attn.q_a_proj",
"model.layers.57.self_attn.q_b_proj",
"model.layers.58.mlp.gate",
"model.layers.58.mlp.shared_experts.down_proj",
"model.layers.58.mlp.shared_experts.gate_proj",
"model.layers.58.mlp.shared_experts.up_proj",
"model.layers.58.self_attn.indexer.weights_proj",
"model.layers.58.self_attn.indexer.wk",
"model.layers.58.self_attn.indexer.wq_b",
"model.layers.58.self_attn.kv_a_proj_with_mqa",
"model.layers.58.self_attn.kv_b_proj",
"model.layers.58.self_attn.o_proj",
"model.layers.58.self_attn.q_a_proj",
"model.layers.58.self_attn.q_b_proj",
"model.layers.59.mlp.gate",
"model.layers.59.mlp.shared_experts.down_proj",
"model.layers.59.mlp.shared_experts.gate_proj",
"model.layers.59.mlp.shared_experts.up_proj",
"model.layers.59.self_attn.indexer.weights_proj",
"model.layers.59.self_attn.indexer.wk",
"model.layers.59.self_attn.indexer.wq_b",
"model.layers.59.self_attn.kv_a_proj_with_mqa",
"model.layers.59.self_attn.kv_b_proj",
"model.layers.59.self_attn.o_proj",
"model.layers.59.self_attn.q_a_proj",
"model.layers.59.self_attn.q_b_proj",
"model.layers.6.mlp.gate",
"model.layers.6.mlp.shared_experts.down_proj",
"model.layers.6.mlp.shared_experts.gate_proj",
"model.layers.6.mlp.shared_experts.up_proj",
"model.layers.6.self_attn.indexer.weights_proj",
"model.layers.6.self_attn.indexer.wk",
"model.layers.6.self_attn.indexer.wq_b",
"model.layers.6.self_attn.kv_a_proj_with_mqa",
"model.layers.6.self_attn.kv_b_proj",
"model.layers.6.self_attn.o_proj",
"model.layers.6.self_attn.q_a_proj",
"model.layers.6.self_attn.q_b_proj",
"model.layers.60.mlp.gate",
"model.layers.60.mlp.shared_experts.down_proj",
"model.layers.60.mlp.shared_experts.gate_proj",
"model.layers.60.mlp.shared_experts.up_proj",
"model.layers.60.self_attn.indexer.weights_proj",
"model.layers.60.self_attn.indexer.wk",
"model.layers.60.self_attn.indexer.wq_b",
"model.layers.60.self_attn.kv_a_proj_with_mqa",
"model.layers.60.self_attn.kv_b_proj",
"model.layers.60.self_attn.o_proj",
"model.layers.60.self_attn.q_a_proj",
"model.layers.60.self_attn.q_b_proj",
"model.layers.61.mlp.gate",
"model.layers.61.mlp.shared_experts.down_proj",
"model.layers.61.mlp.shared_experts.gate_proj",
"model.layers.61.mlp.shared_experts.up_proj",
"model.layers.61.self_attn.indexer.weights_proj",
"model.layers.61.self_attn.indexer.wk",
"model.layers.61.self_attn.indexer.wq_b",
"model.layers.61.self_attn.kv_a_proj_with_mqa",
"model.layers.61.self_attn.kv_b_proj",
"model.layers.61.self_attn.o_proj",
"model.layers.61.self_attn.q_a_proj",
"model.layers.61.self_attn.q_b_proj",
"model.layers.62.mlp.gate",
"model.layers.62.mlp.shared_experts.down_proj",
"model.layers.62.mlp.shared_experts.gate_proj",
"model.layers.62.mlp.shared_experts.up_proj",
"model.layers.62.self_attn.indexer.weights_proj",
"model.layers.62.self_attn.indexer.wk",
"model.layers.62.self_attn.indexer.wq_b",
"model.layers.62.self_attn.kv_a_proj_with_mqa",
"model.layers.62.self_attn.kv_b_proj",
"model.layers.62.self_attn.o_proj",
"model.layers.62.self_attn.q_a_proj",
"model.layers.62.self_attn.q_b_proj",
"model.layers.63.mlp.gate",
"model.layers.63.mlp.shared_experts.down_proj",
"model.layers.63.mlp.shared_experts.gate_proj",
"model.layers.63.mlp.shared_experts.up_proj",
"model.layers.63.self_attn.indexer.weights_proj",
"model.layers.63.self_attn.indexer.wk",
"model.layers.63.self_attn.indexer.wq_b",
"model.layers.63.self_attn.kv_a_proj_with_mqa",
"model.layers.63.self_attn.kv_b_proj",
"model.layers.63.self_attn.o_proj",
"model.layers.63.self_attn.q_a_proj",
"model.layers.63.self_attn.q_b_proj",
"model.layers.64.mlp.gate",
"model.layers.64.mlp.shared_experts.down_proj",
"model.layers.64.mlp.shared_experts.gate_proj",
"model.layers.64.mlp.shared_experts.up_proj",
"model.layers.64.self_attn.indexer.weights_proj",
"model.layers.64.self_attn.indexer.wk",
"model.layers.64.self_attn.indexer.wq_b",
"model.layers.64.self_attn.kv_a_proj_with_mqa",
"model.layers.64.self_attn.kv_b_proj",
"model.layers.64.self_attn.o_proj",
"model.layers.64.self_attn.q_a_proj",
"model.layers.64.self_attn.q_b_proj",
"model.layers.65.mlp.gate",
"model.layers.65.mlp.shared_experts.down_proj",
"model.layers.65.mlp.shared_experts.gate_proj",
"model.layers.65.mlp.shared_experts.up_proj",
"model.layers.65.self_attn.indexer.weights_proj",
"model.layers.65.self_attn.indexer.wk",
"model.layers.65.self_attn.indexer.wq_b",
"model.layers.65.self_attn.kv_a_proj_with_mqa",
"model.layers.65.self_attn.kv_b_proj",
"model.layers.65.self_attn.o_proj",
"model.layers.65.self_attn.q_a_proj",
"model.layers.65.self_attn.q_b_proj",
"model.layers.66.mlp.gate",
"model.layers.66.mlp.shared_experts.down_proj",
"model.layers.66.mlp.shared_experts.gate_proj",
"model.layers.66.mlp.shared_experts.up_proj",
"model.layers.66.self_attn.indexer.weights_proj",
"model.layers.66.self_attn.indexer.wk",
"model.layers.66.self_attn.indexer.wq_b",
"model.layers.66.self_attn.kv_a_proj_with_mqa",
"model.layers.66.self_attn.kv_b_proj",
"model.layers.66.self_attn.o_proj",
"model.layers.66.self_attn.q_a_proj",
"model.layers.66.self_attn.q_b_proj",
"model.layers.67.mlp.gate",
"model.layers.67.mlp.shared_experts.down_proj",
"model.layers.67.mlp.shared_experts.gate_proj",
"model.layers.67.mlp.shared_experts.up_proj",
"model.layers.67.self_attn.indexer.weights_proj",
"model.layers.67.self_attn.indexer.wk",
"model.layers.67.self_attn.indexer.wq_b",
"model.layers.67.self_attn.kv_a_proj_with_mqa",
"model.layers.67.self_attn.kv_b_proj",
"model.layers.67.self_attn.o_proj",
"model.layers.67.self_attn.q_a_proj",
"model.layers.67.self_attn.q_b_proj",
"model.layers.68.mlp.gate",
"model.layers.68.mlp.shared_experts.down_proj",
"model.layers.68.mlp.shared_experts.gate_proj",
"model.layers.68.mlp.shared_experts.up_proj",
"model.layers.68.self_attn.indexer.weights_proj",
"model.layers.68.self_attn.indexer.wk",
"model.layers.68.self_attn.indexer.wq_b",
"model.layers.68.self_attn.kv_a_proj_with_mqa",
"model.layers.68.self_attn.kv_b_proj",
"model.layers.68.self_attn.o_proj",
"model.layers.68.self_attn.q_a_proj",
"model.layers.68.self_attn.q_b_proj",
"model.layers.69.mlp.gate",
"model.layers.69.mlp.shared_experts.down_proj",
"model.layers.69.mlp.shared_experts.gate_proj",
"model.layers.69.mlp.shared_experts.up_proj",
"model.layers.69.self_attn.indexer.weights_proj",
"model.layers.69.self_attn.indexer.wk",
"model.layers.69.self_attn.indexer.wq_b",
"model.layers.69.self_attn.kv_a_proj_with_mqa",
"model.layers.69.self_attn.kv_b_proj",
"model.layers.69.self_attn.o_proj",
"model.layers.69.self_attn.q_a_proj",
"model.layers.69.self_attn.q_b_proj",
"model.layers.7.mlp.gate",
"model.layers.7.mlp.shared_experts.down_proj",
"model.layers.7.mlp.shared_experts.gate_proj",
"model.layers.7.mlp.shared_experts.up_proj",
"model.layers.7.self_attn.indexer.weights_proj",
"model.layers.7.self_attn.indexer.wk",
"model.layers.7.self_attn.indexer.wq_b",
"model.layers.7.self_attn.kv_a_proj_with_mqa",
"model.layers.7.self_attn.kv_b_proj",
"model.layers.7.self_attn.o_proj",
"model.layers.7.self_attn.q_a_proj",
"model.layers.7.self_attn.q_b_proj",
"model.layers.70.mlp.gate",
"model.layers.70.mlp.shared_experts.down_proj",
"model.layers.70.mlp.shared_experts.gate_proj",
"model.layers.70.mlp.shared_experts.up_proj",
"model.layers.70.self_attn.indexer.weights_proj",
"model.layers.70.self_attn.indexer.wk",
"model.layers.70.self_attn.indexer.wq_b",
"model.layers.70.self_attn.kv_a_proj_with_mqa",
"model.layers.70.self_attn.kv_b_proj",
"model.layers.70.self_attn.o_proj",
"model.layers.70.self_attn.q_a_proj",
"model.layers.70.self_attn.q_b_proj",
"model.layers.71.mlp.gate",
"model.layers.71.mlp.shared_experts.down_proj",
"model.layers.71.mlp.shared_experts.gate_proj",
"model.layers.71.mlp.shared_experts.up_proj",
"model.layers.71.self_attn.indexer.weights_proj",
"model.layers.71.self_attn.indexer.wk",
"model.layers.71.self_attn.indexer.wq_b",
"model.layers.71.self_attn.kv_a_proj_with_mqa",
"model.layers.71.self_attn.kv_b_proj",
"model.layers.71.self_attn.o_proj",
"model.layers.71.self_attn.q_a_proj",
"model.layers.71.self_attn.q_b_proj",
"model.layers.72.mlp.gate",
"model.layers.72.mlp.shared_experts.down_proj",
"model.layers.72.mlp.shared_experts.gate_proj",
"model.layers.72.mlp.shared_experts.up_proj",
"model.layers.72.self_attn.indexer.weights_proj",
"model.layers.72.self_attn.indexer.wk",
"model.layers.72.self_attn.indexer.wq_b",
"model.layers.72.self_attn.kv_a_proj_with_mqa",
"model.layers.72.self_attn.kv_b_proj",
"model.layers.72.self_attn.o_proj",
"model.layers.72.self_attn.q_a_proj",
"model.layers.72.self_attn.q_b_proj",
"model.layers.73.mlp.gate",
"model.layers.73.mlp.shared_experts.down_proj",
"model.layers.73.mlp.shared_experts.gate_proj",
"model.layers.73.mlp.shared_experts.up_proj",
"model.layers.73.self_attn.indexer.weights_proj",
"model.layers.73.self_attn.indexer.wk",
"model.layers.73.self_attn.indexer.wq_b",
"model.layers.73.self_attn.kv_a_proj_with_mqa",
"model.layers.73.self_attn.kv_b_proj",
"model.layers.73.self_attn.o_proj",
"model.layers.73.self_attn.q_a_proj",
"model.layers.73.self_attn.q_b_proj",
"model.layers.74.mlp.gate",
"model.layers.74.mlp.shared_experts.down_proj",
"model.layers.74.mlp.shared_experts.gate_proj",
"model.layers.74.mlp.shared_experts.up_proj",
"model.layers.74.self_attn.indexer.weights_proj",
"model.layers.74.self_attn.indexer.wk",
"model.layers.74.self_attn.indexer.wq_b",
"model.layers.74.self_attn.kv_a_proj_with_mqa",
"model.layers.74.self_attn.kv_b_proj",
"model.layers.74.self_attn.o_proj",
"model.layers.74.self_attn.q_a_proj",
"model.layers.74.self_attn.q_b_proj",
"model.layers.75.mlp.gate",
"model.layers.75.mlp.shared_experts.down_proj",
"model.layers.75.mlp.shared_experts.gate_proj",
"model.layers.75.mlp.shared_experts.up_proj",
"model.layers.75.self_attn.indexer.weights_proj",
"model.layers.75.self_attn.indexer.wk",
"model.layers.75.self_attn.indexer.wq_b",
"model.layers.75.self_attn.kv_a_proj_with_mqa",
"model.layers.75.self_attn.kv_b_proj",
"model.layers.75.self_attn.o_proj",
"model.layers.75.self_attn.q_a_proj",
"model.layers.75.self_attn.q_b_proj",
"model.layers.76.mlp.gate",
"model.layers.76.mlp.shared_experts.down_proj",
"model.layers.76.mlp.shared_experts.gate_proj",
"model.layers.76.mlp.shared_experts.up_proj",
"model.layers.76.self_attn.indexer.weights_proj",
"model.layers.76.self_attn.indexer.wk",
"model.layers.76.self_attn.indexer.wq_b",
"model.layers.76.self_attn.kv_a_proj_with_mqa",
"model.layers.76.self_attn.kv_b_proj",
"model.layers.76.self_attn.o_proj",
"model.layers.76.self_attn.q_a_proj",
"model.layers.76.self_attn.q_b_proj",
"model.layers.77.mlp.gate",
"model.layers.77.mlp.shared_experts.down_proj",
"model.layers.77.mlp.shared_experts.gate_proj",
"model.layers.77.mlp.shared_experts.up_proj",
"model.layers.77.self_attn.indexer.weights_proj",
"model.layers.77.self_attn.indexer.wk",
"model.layers.77.self_attn.indexer.wq_b",
"model.layers.77.self_attn.kv_a_proj_with_mqa",
"model.layers.77.self_attn.kv_b_proj",
"model.layers.77.self_attn.o_proj",
"model.layers.77.self_attn.q_a_proj",
"model.layers.77.self_attn.q_b_proj",
"model.layers.78.mlp.gate",
"model.layers.78.mlp.shared_experts.down_proj",
"model.layers.78.mlp.shared_experts.gate_proj",
"model.layers.78.mlp.shared_experts.up_proj",
"model.layers.78.self_attn.indexer.weights_proj",
"model.layers.78.self_attn.indexer.wk",
"model.layers.78.self_attn.indexer.wq_b",
"model.layers.78.self_attn.kv_a_proj_with_mqa",
"model.layers.78.self_attn.kv_b_proj",
"model.layers.78.self_attn.o_proj",
"model.layers.78.self_attn.q_a_proj",
"model.layers.78.self_attn.q_b_proj",
"model.layers.8.mlp.gate",
"model.layers.8.mlp.shared_experts.down_proj",
"model.layers.8.mlp.shared_experts.gate_proj",
"model.layers.8.mlp.shared_experts.up_proj",
"model.layers.8.self_attn.indexer.weights_proj",
"model.layers.8.self_attn.indexer.wk",
"model.layers.8.self_attn.indexer.wq_b",
"model.layers.8.self_attn.kv_a_proj_with_mqa",
"model.layers.8.self_attn.kv_b_proj",
"model.layers.8.self_attn.o_proj",
"model.layers.8.self_attn.q_a_proj",
"model.layers.8.self_attn.q_b_proj",
"model.layers.9.mlp.gate",
"model.layers.9.mlp.shared_experts.down_proj",
"model.layers.9.mlp.shared_experts.gate_proj",
"model.layers.9.mlp.shared_experts.up_proj",
"model.layers.9.self_attn.indexer.weights_proj",
"model.layers.9.self_attn.indexer.wk",
"model.layers.9.self_attn.indexer.wq_b",
"model.layers.9.self_attn.kv_a_proj_with_mqa",
"model.layers.9.self_attn.kv_b_proj",
"model.layers.9.self_attn.o_proj",
"model.layers.9.self_attn.q_a_proj",
"model.layers.9.self_attn.q_b_proj"
],
"algo_config": null,
"softmax_quant_spec": null,
"quant_method": "quark",
"layer_type_quant_config": {},
"layer_quant_config": {},
"kv_cache_quant_config": {},
"kv_cache_post_rope": false,
"quant_mode": "eager_mode",
"version": "0.12+6ff6457c80",
"export": {
"kv_cache_group": [],
"min_kv_scale": 0.0,
"pack_method": "reorder",
"weight_format": "real_quantized",
"weight_merge_groups": null
}
}
}