| { |
| "architectures": [ |
| "MistralDualModel" |
| ], |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_mistral_dual.MistralDualConfig", |
| "AutoModel": "modeling_mistral_dual.MistralDualModel" |
| }, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 14336, |
| "max_position_embeddings": 32768, |
| "model_type": "mistraldual", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 8, |
| "pad_token_id": 2, |
| "rms_norm_eps": 1e-05, |
| "rope_theta": 1000000.0, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.51.3", |
| "use_cache": false, |
| "vocab_size": 32000 |
| } |
|
|
