configs/text_encoder_config.json

{
  "return_dict": true,
  "output_hidden_states": false,
  "dtype": "float32",
  "chunk_size_feed_forward": 0,
  "is_encoder_decoder": false,
  "architectures": [
    "CLIPTextModel"
  ],
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1"
  },
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1
  },
  "problem_type": null,
  "_name_or_path": "/root/.cache/huggingface/hub/models--stable-diffusion-v1-5--stable-diffusion-v1-5/snapshots/451f4fe16113bff5a5d2269ed5ad43b0592e9a14/text_encoder",
  "transformers_version": "5.0.0",
  "dropout": 0.0,
  "model_type": "clip_text_model",
  "pad_token_id": 1,
  "bos_token_id": 0,
  "eos_token_id": 2,
  "vocab_size": 49408,
  "hidden_size": 768,
  "intermediate_size": 3072,
  "projection_dim": 768,
  "num_hidden_layers": 12,
  "num_attention_heads": 12,
  "max_position_embeddings": 77,
  "layer_norm_eps": 1e-05,
  "hidden_act": "quick_gelu",
  "initializer_range": 0.02,
  "initializer_factor": 1.0,
  "attention_dropout": 0.0,
  "output_attentions": false
}