text_encoder/config.json

{
  "architectures": [
    "CLIPTextModelWithProjection"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 0,
  "dropout": 0.0,
  "eos_token_id": 2,
  "hidden_act": "quick_gelu",
  "hidden_size": 768,
  "initializer_factor": 1.0,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 77,
  "model_type": "clip_text_model",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 1,
  "projection_dim": 768,
  "torch_dtype": "float16",
  "transformers_version": "4.41.2",
  "vocab_size": 49408
}