{
  "_name_or_path": "zhiqiulin/clip-flant5-xxl",
  "architectures": [
    "CLIPT5ForConditionalGeneration"
  ],
  "classifier_dropout": 0.0,
  "d_ff": 10240,
  "d_kv": 64,
  "d_model": 4096,
  "decoder_start_token_id": 0,
  "dense_act_fn": "gelu_new",
  "dropout_rate": 0.1,
  "eos_token_id": 1,
  "feed_forward_proj": "gated-gelu",
  "freeze_mm_mlp_adapter": false,
  "image_aspect_ratio": "pad",
  "image_grid_pinpoints": null,
  "initializer_factor": 1.0,
  "is_encoder_decoder": true,
  "is_gated_act": true,
  "layer_norm_epsilon": 1e-06,
  "mm_hidden_size": 1024,
  "mm_projector_type": "mlp2x_gelu",
  "mm_use_im_patch_token": false,
  "mm_use_im_start_end": false,
  "mm_vision_select_feature": "patch",
  "mm_vision_select_layer": -2,
  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
  "model_type": "clip_t5",
  "num_decoder_layers": 24,
  "num_heads": 64,
  "num_layers": 24,
  "output_hidden_states": true,
  "output_past": true,
  "pad_token_id": 0,
  "prefix_mask": false,
  "relative_attention_max_distance": 128,
  "relative_attention_num_buckets": 32,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.41.2",
  "tune_mm_mlp_adapter": false,
  "use_cache": true,
  "use_mm_proj": true,
  "vocab_size": 32128
}