text_encoder/config.json

{
  "architectures": [
    "CLIPTextModel"
  ],
  "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,
  "quantization_config": {
    "_load_in_4bit": false,
    "_load_in_8bit": true,
    "bnb_4bit_compute_dtype": "bfloat16",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "nf4",
    "bnb_4bit_use_double_quant": false,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": [],
    "llm_int8_threshold": 6.0,
    "load_in_4bit": false,
    "load_in_8bit": true,
    "quant_method": "bitsandbytes"
  },
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.0",
  "vocab_size": 49408
}