| { | |
| "architectures": [ | |
| "Eagle3DeepseekV2ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 163584, | |
| "draft_vocab_size": 163840, | |
| "dtype": "bfloat16", | |
| "eagle_config": { | |
| "eagle_aux_hidden_state_layer_ids": [ | |
| 2, | |
| 30, | |
| 58 | |
| ], | |
| "use_aux_hidden_state": true | |
| }, | |
| "eos_token_id": 163585, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 7168, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18432, | |
| "max_position_embeddings": 262144, | |
| "max_window_layers": 48, | |
| "mlp_bias": false, | |
| "model_type": "kimi_k2", | |
| "num_attention_heads": 64, | |
| "num_hidden_layers": 1, | |
| "num_key_value_heads": 64, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "beta_fast": 32.0, | |
| "beta_slow": 1.0, | |
| "factor": 64.0, | |
| "mscale": 1.0, | |
| "mscale_all_dim": 1.0, | |
| "original_max_position_embeddings": 4096, | |
| "type": "yarn" | |
| }, | |
| "rope_theta": 50000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.57.1", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 163840, | |
| "qk_nope_head_dim": 128, | |
| "qk_rope_head_dim": 64, | |
| "q_lora_rank": 1536, | |
| "kv_lora_rank": 512, | |
| "v_head_dim": 128, | |
| "first_k_dense_replace": 1, | |
| "moe_layer_freq": 1 | |
| } |