| { |
| "architectures": [ |
| "HYV3ForCausalLM" |
| ], |
| "bos_token_id": 120000, |
| "enable_attention_fp32_softmax": false, |
| "enable_lm_head_fp32": true, |
| "enable_moe_fp32_combine": false, |
| "eod_token_id": 120026, |
| "eos_token_id": 120025, |
| "expert_hidden_dim": 1536, |
| "first_k_dense_replace": 1, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "initializer_range": 0.006, |
| "intermediate_size": 13312, |
| "max_position_embeddings": 262144, |
| "model_type": "hy_v3", |
| "moe_intermediate_size": 1536, |
| "moe_router_enable_expert_bias": true, |
| "moe_router_use_sigmoid": true, |
| "num_attention_heads": 64, |
| "num_experts": 192, |
| "num_experts_per_tok": 8, |
| "num_hidden_layers": 80, |
| "num_key_value_heads": 8, |
| "num_nextn_predict_layers": 1, |
| "num_shared_experts": 1, |
| "output_router_logits": true, |
| "pad_token_id": 120002, |
| "qk_norm": true, |
| "quantization": { |
| "group_size": 64, |
| "bits": 8, |
| "mode": "affine", |
| "model.layers.1.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.2.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.3.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.38.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.39.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.40.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.41.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.42.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.43.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.44.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.45.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.46.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.47.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.48.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.49.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.50.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.51.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.52.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.53.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.54.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.55.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.56.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.57.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.58.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.59.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.60.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.61.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.62.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.63.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.64.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.65.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.66.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.67.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.68.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.69.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.70.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.71.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.72.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.73.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.74.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.75.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.76.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.77.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.78.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.79.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| } |
| }, |
| "quantization_config": { |
| "group_size": 64, |
| "bits": 8, |
| "mode": "affine", |
| "model.layers.1.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.2.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.3.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.38.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.39.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.40.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.41.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.42.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.43.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.44.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.45.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.46.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.47.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.48.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.49.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.50.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.51.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.52.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.53.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.54.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.55.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.56.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.57.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.58.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.59.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.60.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.61.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.62.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.63.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.64.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.65.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.66.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.67.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.68.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.69.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.70.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.71.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.72.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.73.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.74.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.75.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.76.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.77.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.78.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.79.mlp.router.gate": { |
| "group_size": 64, |
| "bits": 8 |
| } |
| }, |
| "rms_norm_eps": 1e-05, |
| "rope_parameters": { |
| "rope_theta": 11158840.0, |
| "rope_type": "default" |
| }, |
| "route_norm": true, |
| "router_scaling_factor": 2.826, |
| "sep_token_id": 120007, |
| "tie_word_embeddings": false, |
| "transformers_version": "5.6.0", |
| "use_cache": true, |
| "use_grouped_mm": false, |
| "vocab_size": 120832 |
| } |