pytorch/config.json

{
  "_name_or_path": "LazarusNLP/all-indo-e5-small-v4",
  "architectures": [
    "BertModel"
  ],
  "attention_probs_dropout_prob": 0.1,
  "classifier_dropout": null,
  "dtype": "float32",
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 384,
  "initializer_range": 0.02,
  "intermediate_size": 1536,
  "language": "id",
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "model_type": "bert",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 0,
  "position_embedding_type": "absolute",
  "tokenizer_class": "XLMRobertaTokenizer",
  "transformers_version": "4.56.0",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_size": 250037,
  "task_specific_params": {
    "sentence_similarity": {
      "max_length": 384,
      "pooling_mode": "mean"
    }
  },
  "tags": [
    "sentence-transformers",
    "feature-extraction",
    "sentence-similarity",
    "transformers",
    "indonesian",
    "multilingual"
  ]
}