| { | |
| "attention_bias": false, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 3072, | |
| "intermediate_size": 12288, | |
| "max_position_embeddings": 1048576, | |
| "model_type": "laguna", | |
| "num_attention_heads": 72, | |
| "num_hidden_layers": 6, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "sliding_window": 512, | |
| "vocab_size": 100352, | |
| "layer_types": [ | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention" | |
| ], | |
| "rope_theta": 500000.0, | |
| "gating": "per-head", | |
| "architectures": [ | |
| "DFlashLagunaForCausalLM" | |
| ], | |
| "num_experts": 0, | |
| "sliding_windows": [ | |
| 512, | |
| 512, | |
| 512, | |
| 512, | |
| 512, | |
| 512 | |
| ], | |
| "draft_vocab_size": 100352, | |
| "torch_dtype": "bfloat16", | |
| "eagle_aux_hidden_state_layer_ids": [ | |
| 2, | |
| 11, | |
| 20, | |
| 30, | |
| 39, | |
| 48 | |
| ], | |
| "dflash_config": { | |
| "block_size": 16, | |
| "mask_token_id": 12, | |
| "num_target_layers": 48, | |
| "target_layer_ids": [ | |
| 1, | |
| 10, | |
| 19, | |
| 29, | |
| 38, | |
| 47 | |
| ], | |
| "causal": true | |
| } | |
| } | |