{ "architectures": [ "Phi3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "attn_implementation": "sdpa", "auto_map": { "AutoConfig": "configuration_phi3.Phi3Config", "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM" }, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 256, "initializer_range": 0.02, "intermediate_size": 640, "max_position_embeddings": 256, "model_type": "phi3", "num_attention_heads": 8, "num_hidden_layers": 4, "num_key_value_heads": 2, "original_max_position_embeddings": 256, "pad_token_id": 2, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "sliding_window": 255, "tie_word_embeddings": true, "torch_dtype": "float32", "transformers_version": "4.55.4", "use_cache": false, "vocab_size": 48000 }