| { |
| "dense_intermediate_size": 12288, |
| "eos_token_id": 200020, |
| "head_dim": 128, |
| "hidden_size": 6144, |
| "intermediate_size": 3072, |
| "max_position_embeddings": 1048576, |
| "mlp_layer_types": [ |
| "dense", |
| "dense", |
| "dense", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse", |
| "sparse" |
| ], |
| "model_type": "minimax_m3", |
| "num_attention_heads": 64, |
| "num_experts_per_tok": 4, |
| "num_hidden_layers": 60, |
| "num_key_value_heads": 4, |
| "num_local_experts": 128, |
| "quantization": { |
| "group_size": 64, |
| "bits": 3, |
| "mode": "affine", |
| "model.layers.3.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.38.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.39.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.40.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.41.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.42.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.43.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.44.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.45.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.46.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.47.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.48.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.49.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.50.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.51.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.52.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.53.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.54.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.55.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.56.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.57.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.58.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.59.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| } |
| }, |
| "quantization_config": { |
| "group_size": 64, |
| "bits": 3, |
| "mode": "affine", |
| "model.layers.3.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.38.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.39.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.40.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.41.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.42.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.43.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.44.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.45.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.46.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.47.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.48.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.49.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.50.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.51.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.52.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.53.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.54.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.55.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.56.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.57.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.58.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.59.block_sparse_moe.gate": { |
| "group_size": 64, |
| "bits": 8 |
| } |
| }, |
| "rms_norm_eps": 1e-06, |
| "rope_theta": 5000000, |
| "rotary_dim": 64, |
| "routed_scaling_factor": 2.0, |
| "shared_intermediate_size": 3072, |
| "swiglu_alpha": 1.702, |
| "swiglu_limit": 7.0, |
| "tie_word_embeddings": false, |
| "vocab_size": 200064 |
| } |
