| { |
| "architectures": [ |
| "DSparkDraftModel" |
| ], |
| "auto_map": { |
| "": "config.DSparkSpeculatorConfig" |
| }, |
| "aux_hidden_state_layer_ids": [ |
| 2, |
| 24, |
| 46 |
| ], |
| "block_size": 8, |
| "confidence_head_with_markov": true, |
| "draft_vocab_size": 32000, |
| "dtype": "bfloat16", |
| "enable_confidence_head": true, |
| "markov_head_type": "vanilla", |
| "markov_rank": 256, |
| "mask_token_id": 1, |
| "sample_from_anchor": true, |
| "sliding_window_non_causal": false, |
| "speculators_config": { |
| "algorithm": "dspark", |
| "default_proposal_method": "greedy", |
| "proposal_methods": [ |
| { |
| "accept_tolerance": 0.0, |
| "proposal_type": "greedy", |
| "speculative_tokens": 4, |
| "verifier_accept_k": 1 |
| } |
| ], |
| "verifier": { |
| "architectures": [ |
| "Cohere2MoeForCausalLM" |
| ], |
| "name_or_path": "CohereLabs/North-Mini-Code-1.0-w4a16" |
| } |
| }, |
| "speculators_model_type": "dspark", |
| "speculators_version": "0.6.0", |
| "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": null, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 2048, |
| "initializer_range": 0.02, |
| "intermediate_size": 768, |
| "layer_types": [ |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention" |
| ], |
| "max_position_embeddings": 500000, |
| "max_window_layers": 28, |
| "model_type": "qwen3", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 5, |
| "num_key_value_heads": 4, |
| "pad_token_id": null, |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "rope_theta": 50000, |
| "rope_type": "default" |
| }, |
| "sliding_window": 2048, |
| "tie_word_embeddings": false, |
| "use_cache": true, |
| "use_sliding_window": true, |
| "vocab_size": 262144 |
| }, |
| "transformers_version": "5.13.1" |
| } |
|
|