text-encoder/config.json

{
  "architectures": [
    "CLIPTextEncoderOnly"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "utils.CLIPTextEncoderOnlyConfig",
    "AutoModel": "utils.CLIPTextEncoderOnly"
  },
  "bos_token_id": 49406,
  "eos_token_id": 49407,
  "frozen": false,
  "hidden_act": "quick_gelu",
  "hidden_size": 512,
  "initializer_factor": 1.0,
  "initializer_range": 0.02,
  "intermediate_size": 2048,
  "layer_norm_eps": 1e-05,
  "lora": null,
  "max_position_embeddings": 77,
  "model_name": "openai/clip-vit-base-patch32",
  "model_type": "clip_custom_text_model",
  "num_attention_heads": 8,
  "num_hidden_layers": 12,
  "pad_token_id": 1,
  "pretrained": false,
  "projection_dim": 512,
  "torch_dtype": "float32",
  "transformers_version": "4.40.1",
  "vocab_size": 49408
}