| { |
| "architectures": [ |
| "HYV3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 120000, |
| "dtype": "bfloat16", |
| "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": 32, |
| "first_k_dense_replace": 1, |
| "head_dim": 32, |
| "hidden_act": "silu", |
| "hidden_size": 8, |
| "initializer_range": 0.006, |
| "intermediate_size": 32, |
| "max_position_embeddings": 262144, |
| "mlp_bias": false, |
| "mlp_layer_types": [ |
| "dense", |
| "sparse", |
| "sparse", |
| "sparse" |
| ], |
| "model_type": "hy_v3", |
| "moe_intermediate_size": 32, |
| "moe_router_enable_expert_bias": true, |
| "moe_router_use_sigmoid": true, |
| "num_attention_heads": 8, |
| "num_experts": 192, |
| "num_experts_per_tok": 8, |
| "num_hidden_layers": 4, |
| "num_key_value_heads": 4, |
| "num_nextn_predict_layers": 1, |
| "num_shared_experts": 1, |
| "output_router_logits": true, |
| "pad_token_id": 120002, |
| "qk_norm": true, |
| "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": "5.7.0.dev0", |
| "use_cache": true, |
| "use_grouped_mm": false, |
| "vocab_size": 120832 |
| } |
|
|