config.json

{
  "_name_or_path": "Alibaba-NLP/gte-multilingual-base",
  "architectures": [
    "NewForSequenceClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "auto_map": {
    "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
    "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
    "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
    "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
    "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
    "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
    "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
  },
  "classifier_dropout": 0.0,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "id2label": {
    "0": "H\u00f4 h\u1ea5p - Ph\u1ed5i",
    "1": "Chuy\u00ean khoa M\u1eaft",
    "2": "B\u1ec7nh Vi\u00eam gan",
    "3": "N\u1ed9i khoa",
    "4": "Th\u1ea7n kinh",
    "5": "Ti\u00eau ho\u00e1",
    "6": "Tim m\u1ea1ch",
    "7": "Th\u1eadn - Ti\u1ebft ni\u1ec7u",
    "8": "Ti\u1ec3u \u0111\u01b0\u1eddng - N\u1ed9i ti\u1ebft",
    "9": "C\u01a1 X\u01b0\u01a1ng Kh\u1edbp",
    "10": "Tai M\u0169i H\u1ecdng",
    "11": "Ch\u1ea5n th\u01b0\u01a1ng ch\u1ec9nh h\u00ecnh",
    "12": "Ung b\u01b0\u1edbu",
    "13": "Da li\u1ec5u",
    "14": "Nha khoa",
    "15": "Nam h\u1ecdc",
    "16": "Ph\u1ee5c h\u1ed3i ch\u1ee9c n\u0103ng",
    "17": "C\u1ed9t s\u1ed1ng",
    "18": "Nhi khoa",
    "19": "T\u1ea1o h\u00ecnh H\u00e0m M\u1eb7t",
    "20": "Ngo\u1ea1i th\u1ea7n kinh",
    "21": "Ph\u1eabu thu\u1eadt H\u1eadu m\u00f4n - Tr\u1ef1c tr\u00e0ng"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "B\u1ec7nh Vi\u00eam gan": 2,
    "Chuy\u00ean khoa M\u1eaft": 1,
    "Ch\u1ea5n th\u01b0\u01a1ng ch\u1ec9nh h\u00ecnh": 11,
    "C\u01a1 X\u01b0\u01a1ng Kh\u1edbp": 9,
    "C\u1ed9t s\u1ed1ng": 17,
    "Da li\u1ec5u": 13,
    "H\u00f4 h\u1ea5p - Ph\u1ed5i": 0,
    "Nam h\u1ecdc": 15,
    "Ngo\u1ea1i th\u1ea7n kinh": 20,
    "Nha khoa": 14,
    "Nhi khoa": 18,
    "N\u1ed9i khoa": 3,
    "Ph\u1eabu thu\u1eadt H\u1eadu m\u00f4n - Tr\u1ef1c tr\u00e0ng": 21,
    "Ph\u1ee5c h\u1ed3i ch\u1ee9c n\u0103ng": 16,
    "Tai M\u0169i H\u1ecdng": 10,
    "Th\u1ea7n kinh": 4,
    "Th\u1eadn - Ti\u1ebft ni\u1ec7u": 7,
    "Tim m\u1ea1ch": 6,
    "Ti\u00eau ho\u00e1": 5,
    "Ti\u1ec3u \u0111\u01b0\u1eddng - N\u1ed9i ti\u1ebft": 8,
    "T\u1ea1o h\u00ecnh H\u00e0m M\u1eb7t": 19,
    "Ung b\u01b0\u1edbu": 12
  },
  "layer_norm_eps": 1e-12,
  "layer_norm_type": "layer_norm",
  "logn_attention_clip1": false,
  "logn_attention_scale": false,
  "max_position_embeddings": 8192,
  "model_type": "new",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pack_qkv": true,
  "pad_token_id": 1,
  "position_embedding_type": "rope",
  "problem_type": "single_label_classification",
  "rope_scaling": {
    "factor": 8.0,
    "type": "ntk"
  },
  "rope_theta": 20000,
  "torch_dtype": "float32",
  "transformers_version": "4.47.1",
  "type_vocab_size": 1,
  "unpad_inputs": false,
  "use_memory_efficient_attention": false,
  "vocab_size": 250048
}