config.json

{
  "model_type": "sentence_transformer",
  "architecture": "BertModel",
  "vocab_size": 32000,
  "hidden_size": 768,
  "num_hidden_layers": 12,
  "num_attention_heads": 12,
  "intermediate_size": 3072,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "attention_probs_dropout_prob": 0.1,
  "max_position_embeddings": 512,
  "type_vocab_size": 2,
  "initializer_range": 0.02,
  "layer_norm_eps": 1e-12,
  "pooling_mode": "mean",
  "languages": ["bn", "en"],
  "training": {
    "num_epochs": 5,
    "batch_size": 32,
    "learning_rate": 2e-5,
    "warmup_steps": 1000,
    "loss_function": "cosine_similarity"
  }
}