{ "architectures": [ "Phi3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_phi3.Phi3Config", "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM" }, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 192, "initializer_range": 0.1, "intermediate_size": 256, "max_position_embeddings": 131072, "model_type": "phi3", "num_attention_heads": 4, "num_hidden_layers": 4, "num_key_value_heads": 2, "original_max_position_embeddings": 4096, "pad_token_id": 32000, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": { "long_factor": [ 1.0700000524520874, 1.149999976158142, 1.5699999332427979, 2.129999876022339, 3.009999990463257, 6.950000286102295, 9.930000305175781, 11.130000114440918, 15.409998893737793, 37.279998779296875, 38.599998474121094, 46.20000457763672, 53.66000747680664, 56.89738845825195, 59.98738479614258, 60.887386322021484, 62.91739273071289, 63.41739273071289, 63.83739471435547, 63.93739700317383, 64.11434936523438, 64.15435028076172, 64.24435424804688, 64.69000244140625 ], "short_factor": [ 1.1, 1.1, 1.3500000000000003, 1.4000000000000004, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.0500000000000007, 2.0500000000000007, 2.0500000000000007, 2.1000000000000005, 2.25, 2.25, 2.25, 2.4499999999999993, 2.6999999999999984, 2.7499999999999982, 2.8999999999999977 ], "type": "longrope" }, "rope_theta": 10000.0, "sliding_window": 262144, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.55.4", "use_cache": true, "vocab_size": 32064 }