| { | |
| "architectures": [ | |
| "Qwen3NextForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "decoder_sparse_step": 1, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 151645, | |
| "full_attention_interval": 4, | |
| "head_dim": 256, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 5120, | |
| "layer_types": [ | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention" | |
| ], | |
| "linear_conv_kernel_dim": 4, | |
| "linear_key_head_dim": 128, | |
| "linear_num_key_heads": 16, | |
| "linear_num_value_heads": 32, | |
| "linear_value_head_dim": 128, | |
| "max_position_embeddings": 262144, | |
| "mlp_only_layers": [], | |
| "model_type": "qwen3_next", | |
| "moe_intermediate_size": 512, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 16, | |
| "num_experts": 512, | |
| "num_experts_per_tok": 10, | |
| "num_hidden_layers": 48, | |
| "num_key_value_heads": 2, | |
| "output_router_logits": false, | |
| "partial_rotary_factor": 0.25, | |
| "quantization_config": { | |
| "autoround_version": "0.7.0", | |
| "bits": 4, | |
| "data_type": "int", | |
| "extra_config": { | |
| "model.layers.0.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.0.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.0.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.0.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.0.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.1.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.1.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.1.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.1.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.1.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.10.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.10.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.10.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.10.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.10.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.11.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.11.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.11.self_attn.k_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.11.self_attn.o_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.11.self_attn.q_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.11.self_attn.v_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.12.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.12.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.12.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.12.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.12.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.13.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.13.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.13.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.13.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.13.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.14.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.14.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.14.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.14.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.14.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.15.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.15.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.15.self_attn.k_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.15.self_attn.o_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.15.self_attn.q_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.15.self_attn.v_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.16.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.16.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.16.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.16.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.16.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.17.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.17.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.17.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.17.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.17.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.18.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.18.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.18.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.18.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.18.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.19.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.19.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.19.self_attn.k_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.19.self_attn.o_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.19.self_attn.q_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.19.self_attn.v_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.2.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.2.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.2.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.2.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.2.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.20.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.20.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.20.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.20.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.20.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.21.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.21.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.21.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.21.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.21.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.22.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.22.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.22.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.22.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.22.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.23.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.23.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.23.self_attn.k_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.23.self_attn.o_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.23.self_attn.q_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.23.self_attn.v_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.24.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.24.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.24.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.24.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.24.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.25.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.25.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.25.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.25.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.25.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.26.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.26.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.26.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.26.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.26.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.27.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.27.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.27.self_attn.k_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.27.self_attn.o_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.27.self_attn.q_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.27.self_attn.v_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.28.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.28.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.28.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.28.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.28.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.29.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.29.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.29.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.29.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.29.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.3.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.3.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.3.self_attn.k_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.3.self_attn.o_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.3.self_attn.q_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.3.self_attn.v_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.30.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.30.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.30.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.30.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.30.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.31.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.31.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.31.self_attn.k_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.31.self_attn.o_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.31.self_attn.q_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.31.self_attn.v_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.32.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.32.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.32.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.32.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.32.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.33.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.33.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.33.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.33.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.33.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.34.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.34.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.34.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.34.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.34.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.35.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.35.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.35.self_attn.k_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.35.self_attn.o_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.35.self_attn.q_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.35.self_attn.v_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.36.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.36.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.36.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.36.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.36.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.37.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.37.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.37.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.37.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.37.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.38.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.38.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.38.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.38.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.38.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.39.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.39.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.39.self_attn.k_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.39.self_attn.o_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.39.self_attn.q_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.39.self_attn.v_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.4.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.4.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.4.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.4.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.4.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.40.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.40.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.40.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.40.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.40.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.41.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.41.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.41.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.41.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.41.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.42.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.42.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.42.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.42.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.42.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.43.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.43.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.43.self_attn.k_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.43.self_attn.o_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.43.self_attn.q_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.43.self_attn.v_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.44.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.44.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.44.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.44.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.44.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.45.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.45.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.45.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.45.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.45.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.46.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.46.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.46.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.46.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.46.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.47.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.47.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.47.self_attn.k_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.47.self_attn.o_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.47.self_attn.q_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.47.self_attn.v_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.5.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.5.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.5.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.5.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.5.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.6.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.6.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.6.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.6.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.6.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.7.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.7.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.7.self_attn.k_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.7.self_attn.o_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.7.self_attn.q_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.7.self_attn.v_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.8.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.8.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.8.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.8.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.8.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| }, | |
| "model.layers.9.linear_attn.in_proj_ba": { | |
| "bits": 8 | |
| }, | |
| "model.layers.9.linear_attn.in_proj_qkvz": { | |
| "bits": 8 | |
| }, | |
| "model.layers.9.linear_attn.out_proj": { | |
| "bits": 8 | |
| }, | |
| "model.layers.9.mlp.gate": { | |
| "bits": 8 | |
| }, | |
| "model.layers.9.mlp.shared_expert_gate": { | |
| "bits": 16 | |
| } | |
| }, | |
| "group_size": 128, | |
| "iters": 0, | |
| "packing_format": "auto_round:auto_gptq", | |
| "quant_method": "auto-round", | |
| "sym": true | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000000, | |
| "router_aux_loss_coef": 0.001, | |
| "shared_expert_intermediate_size": 512, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.57.0.dev0", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| } | |