| { |
| "architectures": [ |
| "DFlashDraftModel" |
| ], |
| "auto_map": { |
| "": "config.DFlashSpeculatorConfig" |
| }, |
| "aux_hidden_state_layer_ids": [ |
| 2, |
| 18, |
| 30, |
| 42, |
| 54, |
| 60 |
| ], |
| "block_size": 16, |
| "draft_vocab_size": 201024, |
| "dtype": "bfloat16", |
| "mask_token_id": 199998, |
| "speculators_config": { |
| "algorithm": "dflash", |
| "default_proposal_method": "greedy", |
| "proposal_methods": [ |
| { |
| "accept_tolerance": 0.0, |
| "proposal_type": "greedy", |
| "speculative_tokens": 15, |
| "verifier_accept_k": 1 |
| } |
| ], |
| "verifier": { |
| "architectures": [ |
| "InklingForConditionalGeneration" |
| ], |
| "name_or_path": "thinkingmachines/Inkling-NVFP4" |
| } |
| }, |
| "speculators_model_type": "dflash", |
| "speculators_version": "0.7.0", |
| "target_hidden_size": null, |
| "tie_word_embeddings": false, |
| "transformer_layer_config": { |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": null, |
| "eos_token_id": 200006, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 6144, |
| "initializer_range": 0.02, |
| "intermediate_size": 24576, |
| "layer_types": [ |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention" |
| ], |
| "max_position_embeddings": 1048576, |
| "max_window_layers": 6, |
| "model_type": "qwen3", |
| "num_attention_heads": 48, |
| "num_hidden_layers": 6, |
| "num_key_value_heads": 8, |
| "pad_token_id": null, |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "rope_theta": 500000.0, |
| "rope_type": "default" |
| }, |
| "sliding_window": 4096, |
| "tie_word_embeddings": false, |
| "use_cache": true, |
| "use_sliding_window": true, |
| "vocab_size": 201024 |
| }, |
| "transformers_version": "5.7.0", |
| "use_embed_norm": true, |
| "logits_mup_width_multiplier": 24.0 |
| } |
