| { | |
| "vocab_size": 32768, | |
| "hidden_size": 1792, | |
| "intermediate_size": 7168, | |
| "num_hidden_layers": 28, | |
| "num_attention_heads": 14, | |
| "num_key_value_heads": 14, | |
| "max_position_embeddings": 2048, | |
| "rope_theta": 100000.0, | |
| "sliding_window": 512, | |
| "layer_types": [ | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention" | |
| ], | |
| "attention_multiplier": 1.2, | |
| "final_logit_softcapping": 15.0, | |
| "aux_layers": [ | |
| 1, | |
| 3, | |
| 5, | |
| 7, | |
| 9, | |
| 11, | |
| 13, | |
| 15, | |
| 17, | |
| 19, | |
| 21, | |
| 23, | |
| 25, | |
| 27 | |
| ], | |
| "aux_gate_dim": 12, | |
| "mix_gate_dim": 24, | |
| "tap_layer": 14, | |
| "use_cache": false, | |
| "architectures": [ | |
| "NanochronoForCausalLM" | |
| ], | |
| "output_hidden_states": false, | |
| "return_dict": true, | |
| "dtype": "bfloat16", | |
| "chunk_size_feed_forward": 0, | |
| "is_encoder_decoder": false, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "problem_type": null, | |
| "bos_token_id": 32759, | |
| "eos_token_id": 32763, | |
| "pad_token_id": 32763, | |
| "tie_word_embeddings": false, | |
| "model_type": "sn38-nanochrono", | |
| "output_attentions": false, | |
| "torch_dtype": "bfloat16" | |
| } | |