| { |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 163584, |
| "eos_token_id": 163586, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 7168, |
| "initializer_range": 0.02, |
| "intermediate_size": 14336, |
| "kv_lora_rank": 512, |
| "layer_types": [ |
| "full_attention", |
| "full_attention", |
| "full_attention" |
| ], |
| "num_attention_heads": 96, |
| "num_hidden_layers": 3, |
| "num_key_value_heads": 96, |
| "pad_token_id": 163839, |
| "q_lora_rank": 1536, |
| "qk_head_dim": 192, |
| "qk_nope_head_dim": 128, |
| "qk_rope_head_dim": 64, |
| "rms_norm_eps": 1e-05, |
| "rope_interleave": true, |
| "rope_parameters": { |
| "rope_type": "yarn", |
| "rope_theta": 1000000.0, |
| "factor": 32.0, |
| "original_max_position_embeddings": 32768, |
| "beta_fast": 32, |
| "beta_slow": 1, |
| "mscale": 1.0, |
| "mscale_all_dim": 0.0, |
| "attn_factor": 0.7426255848312643 |
| }, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "use_cache": true, |
| "use_sliding_window": false, |
| "v_head_dim": 128, |
| "vocab_size": 163840, |
| "architectures": [ |
| "K3DSparkModel" |
| ], |
| "model_type": "k3_dspark", |
| "max_position_embeddings": 1048576, |
| "rope_theta": 1000000.0, |
| "num_target_layers": 3, |
| "target_hidden_size": 7168, |
| "target_num_hidden_layers": 93, |
| "target_layer_ids": [ |
| 71, |
| 87, |
| 91 |
| ], |
| "mask_token_id": 163839, |
| "markov_rank": 512, |
| "markov_head_type": "vanilla", |
| "enable_confidence_head": true, |
| "confidence_head_with_markov": true, |
| "sample_from_anchor": true, |
| "block_size": 5, |
| "sliding_window_non_causal": false, |
| "full_attention_causal": true, |
| "dflash_config": { |
| "causal": true |
| }, |
| "draft_vocab_size": 163840, |
| "torch_dtype": "bfloat16" |
| } |
|
|