| { |
| "architectures": [ |
| "Qwen3DSparkModel" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "block_size": 5, |
| "bos_token_id": 163584, |
| "confidence_head_with_markov": true, |
| "dflash_config": { |
| "attention_mode": "gqa", |
| "confidence_head_alpha": 1.0, |
| "confidence_head_with_markov": true, |
| "enable_confidence_head": true, |
| "markov_head_type": "vanilla", |
| "markov_rank": 256, |
| "mask_token_id": 163824, |
| "projector_type": "dspark", |
| "target_layer_ids": [ |
| 7, |
| 23, |
| 67, |
| 83, |
| 91 |
| ] |
| }, |
| "draft_vocab_size": 163840, |
| "dtype": "bfloat16", |
| "enable_confidence_head": true, |
| "eos_token_id": 163586, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 7168, |
| "initializer_range": 0.02, |
| "intermediate_size": 14336, |
| "layer_types": [ |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention" |
| ], |
| "markov_head_type": "vanilla", |
| "markov_rank": 256, |
| "max_position_embeddings": 1048576, |
| "max_window_layers": 5, |
| "model_type": "qwen3", |
| "num_attention_heads": 64, |
| "num_hidden_layers": 5, |
| "num_key_value_heads": 16, |
| "num_target_layers": 93, |
| "pad_token_id": 163839, |
| "rms_norm_eps": 1e-05, |
| "rope_parameters": { |
| "factor": 16.0, |
| "original_max_position_embeddings": 65536, |
| "rope_theta": 10000.0, |
| "rope_type": "yarn" |
| }, |
| "rope_scaling": { |
| "factor": 16.0, |
| "original_max_position_embeddings": 65536, |
| "rope_type": "yarn" |
| }, |
| "rope_theta": 10000.0, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "transformers_version": "5.12.1", |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 163840, |
| "is_causal": false |
| } |
|
|
