{ "_name_or_path": "sapienzanlp/Minerva-3B-base-v1.0", "architectures": [ "MistralForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": 8960, "max_position_embeddings": 16384, "model_type": "mistral", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "sliding_window": 2048, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.39.3", "use_cache": false, "vocab_size": 32769 }