pretrain/config.json

{
  "_name_or_path": "microsoft/Phi-3-mini-128k-instruct",
  "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",
    "AutoModelForSequenceClassification": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForSequenceClassification",
    "AutoModelForTokenClassification": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForTokenClassification"
  },
  "balance_loss_coef": 0.0,
  "bos_token_id": 1,
  "clip_smoe": false,
  "dropout": false,
  "embd_pdrop": 0.0,
  "eos_token_id": 32000,
  "freeze_mm_mlp_adapter": false,
  "hidden_act": "silu",
  "hidden_size": 3072,
  "image_aspect_ratio": "square",
  "initializer_range": 0.02,
  "intermediate_size": 8192,
  "local_rank": 0,
  "max_position_embeddings": 131072,
  "mlp_smoe": false,
  "mm_hidden_size": 1024,
  "mm_patch_merge_type": "flat",
  "mm_projector_lr": null,
  "mm_projector_type": "mlp2x_gelu",
  "mm_use_im_patch_token": false,
  "mm_use_im_start_end": false,
  "mm_vision_select_feature": "patch",
  "mm_vision_select_layer": -2,
  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
  "model_type": "llava_phi",
  "num_attention_heads": 32,
  "num_experts": 1,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "num_layers": 3,
  "num_selected": 1,
  "original_max_position_embeddings": 4096,
  "pad_token_id": 32000,
  "resid_pdrop": 0.0,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "long_factor": [
      1.0299999713897705,
      1.0499999523162842,
      1.0499999523162842,
      1.0799999237060547,
      1.2299998998641968,
      1.2299998998641968,
      1.2999999523162842,
      1.4499999284744263,
      1.5999999046325684,
      1.6499998569488525,
      1.8999998569488525,
      2.859999895095825,
      3.68999981880188,
      5.419999599456787,
      5.489999771118164,
      5.489999771118164,
      9.09000015258789,
      11.579999923706055,
      15.65999984741211,
      15.769999504089355,
      15.789999961853027,
      18.360000610351562,
      21.989999771118164,
      23.079999923706055,
      30.009998321533203,
      32.35000228881836,
      32.590003967285156,
      35.56000518798828,
      39.95000457763672,
      53.840003967285156,
      56.20000457763672,
      57.95000457763672,
      59.29000473022461,
      59.77000427246094,
      59.920005798339844,
      61.190006256103516,
      61.96000671386719,
      62.50000762939453,
      63.3700065612793,
      63.48000717163086,
      63.48000717163086,
      63.66000747680664,
      63.850006103515625,
      64.08000946044922,
      64.760009765625,
      64.80001068115234,
      64.81001281738281,
      64.81001281738281
    ],
    "short_factor": [
      1.05,
      1.05,
      1.05,
      1.1,
      1.1,
      1.1500000000000001,
      1.2000000000000002,
      1.2500000000000002,
      1.3000000000000003,
      1.3500000000000003,
      1.5000000000000004,
      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,
      2.000000000000001,
      2.000000000000001,
      2.000000000000001,
      2.000000000000001,
      2.0500000000000007,
      2.0500000000000007,
      2.0500000000000007,
      2.1000000000000005,
      2.1000000000000005,
      2.1000000000000005,
      2.1500000000000004,
      2.1500000000000004,
      2.3499999999999996,
      2.549999999999999,
      2.5999999999999988,
      2.5999999999999988,
      2.7499999999999982,
      2.849999999999998,
      2.849999999999998,
      2.9499999999999975
    ],
    "type": "su"
  },
  "rope_theta": 10000.0,
  "router_z_loss_coef": 0.0,
  "scales": [
    1,
    3
  ],
  "sliding_window": 262144,
  "tie_word_embeddings": false,
  "tokenizer_model_max_length": 2048,
  "tokenizer_padding_side": "right",
  "torch_dtype": "bfloat16",
  "training": true,
  "transformers_version": "4.41.2",
  "tune_mm_mlp_adapter": true,
  "use_cache": true,
  "use_mm_proj": true,
  "vocab_size": 32064
}