| { |
| "architectures": [ |
| "DFlash2DraftModel" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0, |
| "bos_token_id": 200000, |
| "dflash_config": { |
| "attention_mode": "gqa", |
| "block_size": 8, |
| "conv_group_size": 16, |
| "conv_kernel_size": 2, |
| "final_logit_softcapping": 20, |
| "mask_token_id": 200002, |
| "output_multiplier": 0.1767766952966369, |
| "selector_rank": 256, |
| "selector_top_k": 16, |
| "target_layer_ids": [ |
| 1, |
| 16, |
| 30, |
| 44, |
| 59 |
| ] |
| }, |
| "draft_vocab_size": 202048, |
| "dtype": "bfloat16", |
| "eos_token_id": [ |
| 200001, |
| 200008 |
| ], |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 8192, |
| "initializer_range": 0.02, |
| "intermediate_size": 28672, |
| "is_causal": false, |
| "layer_types": [ |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention" |
| ], |
| "max_position_embeddings": 1048576, |
| "max_window_layers": 5, |
| "model_type": "qwen3", |
| "num_attention_heads": 64, |
| "num_hidden_layers": 5, |
| "num_key_value_heads": 8, |
| "num_target_layers": 62, |
| "pad_token_id": 200018, |
| "rms_norm_eps": 1e-05, |
| "rope_parameters": { |
| "rope_theta": 500000, |
| "rope_type": "default" |
| }, |
| "rope_theta": 500000, |
| "sliding_window": 2048, |
| "tie_word_embeddings": false, |
| "transformers_version": "5.12.1", |
| "use_cache": true, |
| "use_sliding_window": true, |
| "vocab_size": 202048 |
| } |
|
|
