| { |
| "architectures": [ |
| "DFlashDraftModel" |
| ], |
| "auto_map": { |
| "": "config.DFlashSpeculatorConfig" |
| }, |
| "aux_hidden_state_layer_ids": null, |
| "base_model_ep_plan": null, |
| "block_size": 8, |
| "draft_vocab_size": 32000, |
| "dtype": "float32", |
| "has_no_defaults_at_init": false, |
| "num_hidden_layers": 3, |
| "speculators_config": { |
| "algorithm": "dflash", |
| "default_proposal_method": "greedy", |
| "proposal_methods": [ |
| { |
| "accept_tolerance": 0.0, |
| "proposal_type": "greedy", |
| "speculative_tokens": 8, |
| "verifier_accept_k": 1 |
| } |
| ], |
| "verifier": { |
| "architectures": [], |
| "name_or_path": "Qwen/Qwen3-8B" |
| } |
| }, |
| "speculators_model_type": "dflash", |
| "speculators_version": "0.5.0.dev42", |
| "target_hidden_size": null, |
| "transformer_layer_config": { |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 12288, |
| "max_position_embeddings": 40960, |
| "mlp_bias": false, |
| "model_type": "llama", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 3, |
| "num_key_value_heads": 8, |
| "pretraining_tp": 1, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "use_cache": true, |
| "vocab_size": 151936 |
| }, |
| "transformers_version": "4.57.6" |
| } |
|
|