{ "model_type": "phi3", "architectures": [ "Phi3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "microsoft/Phi-3-mini-128k-instruct--configuration_phi3.Phi3Config", "AutoModelForCausalLM": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForCausalLM" }, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "original_max_position_embeddings": 4096, "pad_token_id": 32000, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": { "long_factor": [ 1.0700000524520874, 1.1200000047683716, 1.149999976158142, 1.4199999570846558, 1.5699999332427979, 1.7999999523162842, 2.129999876022339, 2.129999876022339, 3.009999990463257, 5.910000324249268, 6.950000286102295, 9.070000648498535, 9.930000305175781, 10.710000038146973, 11.130000114440918, 14.609999656677246, 15.409998893737793, 19.809999465942383, 37.279998779296875, 38.279998779296875, 38.599998474121094, 40.12000274658203, 46.20000457763672, 50.940006256103516, 53.66000747680664, 54.9373893737793, 56.89738845825195, 57.28738784790039, 59.98738479614258, 60.86738586425781, 60.887386322021484, 61.71739196777344, 62.91739273071289, 62.957393646240234, 63.41739273071289, 63.8173942565918, 63.83739471435547, 63.897396087646484, 63.93739700317383, 64.06739807128906, 64.11434936523438, 64.12435150146484, 64.15435028076172, 64.19435119628906, 64.24435424804688, 64.57435607910156, 64.69000244140625, 64.76000213623047 ], "short_factor": [ 1.1, 1.1, 1.1, 1.3000000000000003, 1.3500000000000003, 1.3500000000000003, 1.4000000000000004, 1.5500000000000005, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.0500000000000007, 2.0500000000000007, 2.0500000000000007, 2.0500000000000007, 2.0500000000000007, 2.0500000000000007, 2.1000000000000005, 2.1000000000000005, 2.1500000000000004, 2.25, 2.25, 2.25, 2.25, 2.25, 2.3999999999999995, 2.4499999999999993, 2.499999999999999, 2.6999999999999984, 2.6999999999999984, 2.7499999999999982, 2.799999999999998, 2.8999999999999977, 3.049999999999997 ], "type": "longrope" }, "rope_theta": 10000.0, "sliding_window": 262144, "tie_word_embeddings": false, "torch_dtype": "float32", "transformers_version": "4.42.4", "use_cache": true, "vocab_size": 32064, "peft_type": "LORA", "lora_alpha": 32, "lora_dropout": 0.05, "r": 16, "target_modules": [ "model.layers.15.self_attn.o_proj", "model.layers.18.mlp.gate_up_proj", "model.layers.3.self_attn.o_proj", "model.layers.15.mlp.down_proj", "model.layers.20.self_attn.o_proj", "model.layers.30.self_attn.o_proj", "model.layers.6.mlp.gate_up_proj", "model.layers.17.self_attn.qkv_proj", "model.layers.4.self_attn.qkv_proj", "model.layers.28.self_attn.o_proj", "model.layers.3.mlp.down_proj", "model.layers.19.mlp.down_proj", "model.layers.8.self_attn.o_proj", "model.layers.8.mlp.down_proj", "model.layers.14.self_attn.qkv_proj", "model.layers.23.mlp.gate_up_proj", "model.layers.9.self_attn.qkv_proj", "model.layers.15.self_attn.qkv_proj", "model.layers.2.self_attn.o_proj", "model.layers.26.self_attn.qkv_proj", "model.layers.7.self_attn.qkv_proj", "model.layers.25.self_attn.qkv_proj", "model.layers.22.mlp.gate_up_proj", "model.layers.8.mlp.gate_up_proj", "model.layers.29.mlp.down_proj", "model.layers.30.mlp.down_proj", "model.layers.20.self_attn.qkv_proj", "model.layers.27.self_attn.qkv_proj", "model.layers.31.self_attn.o_proj", "model.layers.13.mlp.down_proj", "model.layers.16.mlp.down_proj", "model.layers.9.mlp.down_proj", "model.layers.7.mlp.gate_up_proj", "model.layers.29.self_attn.qkv_proj", "model.layers.29.mlp.gate_up_proj", "model.layers.7.mlp.down_proj", "model.layers.1.mlp.down_proj", "model.layers.19.self_attn.o_proj", "model.layers.27.mlp.down_proj", "model.layers.26.mlp.gate_up_proj", "model.layers.3.self_attn.qkv_proj", "model.layers.1.mlp.gate_up_proj", "model.layers.17.mlp.gate_up_proj", "model.layers.14.mlp.down_proj", "model.layers.2.mlp.gate_up_proj", "model.layers.11.self_attn.qkv_proj", "model.layers.13.mlp.gate_up_proj", "model.layers.6.mlp.down_proj", "model.layers.19.mlp.gate_up_proj", "model.layers.22.self_attn.qkv_proj", "model.layers.24.mlp.down_proj", "model.layers.18.self_attn.o_proj", "model.layers.10.mlp.gate_up_proj", "model.layers.25.mlp.gate_up_proj", "model.layers.27.mlp.gate_up_proj", "model.layers.5.mlp.gate_up_proj", "model.layers.4.mlp.down_proj", "model.layers.3.mlp.gate_up_proj", "model.layers.15.mlp.gate_up_proj", "model.layers.25.self_attn.o_proj", "model.layers.0.mlp.down_proj", "model.layers.21.self_attn.qkv_proj", "model.layers.12.self_attn.o_proj", "model.layers.28.self_attn.qkv_proj", "model.layers.20.mlp.gate_up_proj", "model.layers.14.mlp.gate_up_proj", "model.layers.20.mlp.down_proj", "model.layers.18.self_attn.qkv_proj", "model.layers.12.self_attn.qkv_proj", "model.layers.25.mlp.down_proj", "model.layers.5.self_attn.qkv_proj", "model.layers.24.mlp.gate_up_proj", "model.layers.23.self_attn.o_proj", "model.layers.17.self_attn.o_proj", "model.layers.6.self_attn.qkv_proj", "model.layers.22.self_attn.o_proj", "model.layers.6.self_attn.o_proj", "model.layers.31.self_attn.qkv_proj", "model.layers.21.self_attn.o_proj", "model.layers.7.self_attn.o_proj", "model.layers.24.self_attn.qkv_proj", "model.layers.16.self_attn.o_proj", "model.layers.16.self_attn.qkv_proj", "model.layers.12.mlp.down_proj", "model.layers.28.mlp.gate_up_proj", "model.layers.0.mlp.gate_up_proj", "model.layers.9.self_attn.o_proj", "model.layers.9.mlp.gate_up_proj", "model.layers.5.self_attn.o_proj", "model.layers.22.mlp.down_proj", "model.layers.24.self_attn.o_proj", "model.layers.10.self_attn.qkv_proj", "model.layers.1.self_attn.qkv_proj", "model.layers.2.mlp.down_proj", "model.layers.0.self_attn.qkv_proj", "model.layers.8.self_attn.qkv_proj", "model.layers.27.self_attn.o_proj", "model.layers.5.mlp.down_proj", "model.layers.0.self_attn.o_proj", "model.layers.26.self_attn.o_proj", "model.layers.29.self_attn.o_proj", "model.layers.17.mlp.down_proj", "model.layers.12.mlp.gate_up_proj", "model.layers.10.mlp.down_proj", "model.layers.14.self_attn.o_proj", "model.layers.13.self_attn.o_proj", "model.layers.11.self_attn.o_proj", "model.layers.23.mlp.down_proj", "model.layers.19.self_attn.qkv_proj", "model.layers.31.mlp.down_proj", "model.layers.23.self_attn.qkv_proj", "model.layers.31.mlp.gate_up_proj", "model.layers.30.mlp.gate_up_proj", "model.layers.4.mlp.gate_up_proj", "model.layers.4.self_attn.o_proj", "model.layers.2.self_attn.qkv_proj", "model.layers.11.mlp.gate_up_proj", "model.layers.13.self_attn.qkv_proj", "model.layers.21.mlp.gate_up_proj", "model.layers.18.mlp.down_proj", "model.layers.26.mlp.down_proj", "model.layers.10.self_attn.o_proj", "model.layers.11.mlp.down_proj", "model.layers.21.mlp.down_proj", "model.layers.30.self_attn.qkv_proj", "model.layers.1.self_attn.o_proj", "model.layers.28.mlp.down_proj", "model.layers.16.mlp.gate_up_proj" ], "num_hidden_layers": 32 }