| { | |
| "_name_or_path": "mistralai/Mistral-7B-v0.1", | |
| "architectures": [ | |
| "MergedMistralForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "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": "mergedmistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 4096, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.44.2", | |
| "use_cache": true, | |
| "vocab_size": 32000, | |
| "num_merged_models": 4, | |
| "non_linearity": null, | |
| "dam_embedding_layer": true, | |
| "dam_layernorms": true, | |
| "uses_base_model": true, | |
| "is_embedding_coef_trainable": false, | |
| "is_norm_coef_trainable": false | |
| } |