{ "architectures": ["PhiForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "gelu", "hidden_size": 3840, "initializer_range": 0.02, "intermediate_size": 15360, "max_position_embeddings": 16384, "model_type": "phi", "num_attention_heads": 32, "num_hidden_layers": 40, "num_key_value_heads": 32, "original_max_position_embeddings": 2048, "pad_token_id": 0, "rope_scaling": { "factor": 8.0, "type": "linear" }, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.36.0", "vocab_size": 32000 }