| { |
| "architectures": [ |
| "Cohere2MoeForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 2, |
| "dtype": "bfloat16", |
| "eos_token_id": 255001, |
| "expert_selection_fn": "sigmoid", |
| "first_k_dense_replace": 1, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 2048, |
| "initializer_range": 0.02, |
| "intermediate_size": 768, |
| "layer_norm_eps": 1e-05, |
| "layer_types": [ |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention" |
| ], |
| "logit_scale": 1.0, |
| "max_position_embeddings": 500000, |
| "model_type": "cohere2_moe", |
| "norm_topk_prob": false, |
| "num_attention_heads": 32, |
| "num_experts": 128, |
| "num_experts_per_tok": 8, |
| "num_hidden_layers": 49, |
| "num_key_value_heads": 4, |
| "num_shared_experts": 0, |
| "pad_token_id": 0, |
| "prefix_dense_intermediate_size": 3072, |
| "prefix_dense_sliding_window_pattern": 1, |
| "quantization": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine", |
| "model.layers.0.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.0.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.0.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.0.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.0.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.1.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.1.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.1.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.1.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.1.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.1.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.2.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.2.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.2.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.2.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.2.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.2.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.3.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.3.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.3.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.3.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.3.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.3.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.38.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.38.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.38.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.38.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.38.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.38.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.39.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.39.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.39.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.39.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.39.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.39.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.40.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.40.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.40.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.40.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.40.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.40.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.41.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.41.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.41.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.41.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.41.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.41.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.42.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.42.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.42.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.42.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.42.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.42.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.43.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.43.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.43.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.43.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.43.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.43.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.44.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.44.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.44.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.44.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.44.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.44.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.45.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.45.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.45.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.45.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.45.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.45.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.46.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.46.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.46.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.46.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.46.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.46.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.47.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.47.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.47.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.47.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.47.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.47.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.48.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.48.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.48.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.48.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.48.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.48.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| } |
| }, |
| "quantization_config": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine", |
| "model.layers.0.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.0.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.0.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.0.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.0.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.1.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.1.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.1.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.1.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.1.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.1.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.2.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.2.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.2.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.2.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.2.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.2.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.3.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.3.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.3.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.3.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.3.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.3.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.38.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.38.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.38.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.38.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.38.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.38.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.39.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.39.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.39.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.39.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.39.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.39.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.40.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.40.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.40.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.40.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.40.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.40.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.41.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.41.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.41.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.41.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.41.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.41.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.42.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.42.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.42.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.42.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.42.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.42.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.43.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.43.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.43.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.43.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.43.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.43.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.44.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.44.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.44.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.44.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.44.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.44.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.45.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.45.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.45.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.45.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.45.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.45.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.46.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.46.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.46.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.46.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.46.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.46.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.47.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.47.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.47.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.47.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.47.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.47.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.48.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.48.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.48.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.48.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.48.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.48.mlp.switch_mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 8 |
| } |
| }, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 50000, |
| "shared_expert_combination_strategy": "average", |
| "sliding_window": 4096, |
| "transformers_version": "5.8.0", |
| "use_cache": true, |
| "use_gated_activation": true, |
| "use_parallel_block": true, |
| "use_parallel_embedding": false, |
| "use_qk_norm": false, |
| "vocab_size": 262144 |
| } |
