sft_full/smoe/config.json

{
  "_name_or_path": "/cm/archive/namnv78/checkpoints/phi35-siglip224/pft",
  "architectures": [
    "LlavaPhiForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_phi3.Phi3Config",
    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
  },
  "balance_loss_coef": 0.1,
  "bos_token_id": 1,
  "clip_smoe": true,
  "dropout": false,
  "embd_pdrop": 0.0,
  "eos_token_id": 32000,
  "freeze_mm_mlp_adapter": false,
  "hidden_act": "silu",
  "hidden_size": 3072,
  "image_aspect_ratio": "pad",
  "initializer_range": 0.02,
  "intermediate_size": 8192,
  "local_rank": 0,
  "max_position_embeddings": 131072,
  "mlp_smoe": true,
  "mm_hidden_size": 1152,
  "mm_patch_merge_type": "flat",
  "mm_projector_lr": null,
  "mm_projector_type": "moe",
  "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": "google/siglip-so400m-patch14-224",
  "model_type": "llava_phi",
  "moe_name": "smoe",
  "num_attention_heads": 32,
  "num_experts": 4,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "num_layers": 3,
  "num_selected": 2,
  "original_max_position_embeddings": 4096,
  "pad_token_id": 32000,
  "resid_pdrop": 0.0,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "long_factor": [
      1.0800000429153442,
      1.1100000143051147,
      1.1399999856948853,
      1.340000033378601,
      1.5899999141693115,
      1.600000023841858,
      1.6200000047683716,
      2.620000123977661,
      3.2300000190734863,
      3.2300000190734863,
      4.789999961853027,
      7.400000095367432,
      7.700000286102295,
      9.09000015258789,
      12.199999809265137,
      17.670000076293945,
      24.46000099182129,
      28.57000160217285,
      30.420001983642578,
      30.840002059936523,
      32.590003967285156,
      32.93000411987305,
      42.320003509521484,
      44.96000289916992,
      50.340003967285156,
      50.45000457763672,
      57.55000305175781,
      57.93000411987305,
      58.21000289916992,
      60.1400032043457,
      62.61000442504883,
      62.62000274658203,
      62.71000289916992,
      63.1400032043457,
      63.1400032043457,
      63.77000427246094,
      63.93000411987305,
      63.96000289916992,
      63.970001220703125,
      64.02999877929688,
      64.06999969482422,
      64.08000183105469,
      64.12000274658203,
      64.41000366210938,
      64.4800033569336,
      64.51000213623047,
      64.52999877929688,
      64.83999633789062
    ],
    "short_factor": [
      1.0,
      1.0199999809265137,
      1.0299999713897705,
      1.0299999713897705,
      1.0499999523162842,
      1.0499999523162842,
      1.0499999523162842,
      1.0499999523162842,
      1.0499999523162842,
      1.0699999332427979,
      1.0999999046325684,
      1.1099998950958252,
      1.1599998474121094,
      1.1599998474121094,
      1.1699998378753662,
      1.2899998426437378,
      1.339999794960022,
      1.679999828338623,
      1.7899998426437378,
      1.8199998140335083,
      1.8499997854232788,
      1.8799997568130493,
      1.9099997282028198,
      1.9399996995925903,
      1.9899996519088745,
      2.0199997425079346,
      2.0199997425079346,
      2.0199997425079346,
      2.0199997425079346,
      2.0199997425079346,
      2.0199997425079346,
      2.0299997329711914,
      2.0299997329711914,
      2.0299997329711914,
      2.0299997329711914,
      2.0299997329711914,
      2.0299997329711914,
      2.0299997329711914,
      2.0299997329711914,
      2.0299997329711914,
      2.0799996852874756,
      2.0899996757507324,
      2.189999580383301,
      2.2199995517730713,
      2.5899994373321533,
      2.729999542236328,
      2.749999523162842,
      2.8399994373321533
    ],
    "type": "longrope"
  },
  "rope_theta": 10000.0,
  "router_z_loss_coef": 0.01,
  "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": "4.43.0",
  "tune_mm_mlp_adapter": false,
  "use_cache": true,
  "use_mm_proj": true,
  "vocab_size": 32064
}