config.json
| 1 | { |
| 2 | "architectures": [ |
| 3 | "MistralForCausalLM" |
| 4 | ], |
| 5 | "attention_dropout": 0.0, |
| 6 | "bos_token_id": 1, |
| 7 | "eos_token_id": 2, |
| 8 | "hidden_act": "silu", |
| 9 | "hidden_size": 4096, |
| 10 | "initializer_range": 0.02, |
| 11 | "intermediate_size": 14336, |
| 12 | "max_position_embeddings": 32768, |
| 13 | "model_type": "mistral", |
| 14 | "num_attention_heads": 32, |
| 15 | "num_hidden_layers": 32, |
| 16 | "num_key_value_heads": 8, |
| 17 | "rms_norm_eps": 1e-05, |
| 18 | "rope_theta": 1000000.0, |
| 19 | "sliding_window": null, |
| 20 | "tie_word_embeddings": false, |
| 21 | "torch_dtype": "bfloat16", |
| 22 | "transformers_version": "4.36.0", |
| 23 | "use_cache": true, |
| 24 | "vocab_size": 32000 |
| 25 | } |
| 26 | |