config.json

{
    "vision_config": {
      "_name_or_path": "",
      "add_cross_attention": false,
      "architectures": null,
      "attention_dropout": 0.0,
      "bad_words_ids": null,
      "bos_token_id": null,
      "chunk_size_feed_forward": 0,
      "cross_attention_hidden_size": null,
      "decoder_start_token_id": null,
      "diversity_penalty": 0.0,
      "do_sample": false,
      "dropout": 0.0,
      "early_stopping": false,
      "encoder_no_repeat_ngram_size": 0,
      "eos_token_id": null,
      "finetuning_task": null,
      "forced_bos_token_id": null,
      "forced_eos_token_id": null,
      "hidden_act": "quick_gelu",
      "hidden_size": 1024,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "image_size": 224,
      "initializer_factor": 1.0,
      "initializer_range": 0.02,
      "intermediate_size": 4096,
      "is_decoder": false,
      "is_encoder_decoder": false,
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "layer_norm_eps": 1e-05,
      "length_penalty": 1.0,
      "max_length": 20,
      "min_length": 0,
      "model_type": "clip_vision_model",
      "no_repeat_ngram_size": 0,
      "num_attention_heads": 16,
      "num_beam_groups": 1,
      "num_beams": 1,
      "num_hidden_layers": 24,
      "num_return_sequences": 1,
      "output_attentions": false,
      "output_hidden_states": false,
      "output_scores": false,
      "pad_token_id": null,
      "patch_size": 14,
      "prefix": null,
      "problem_type": null,
      "projection_dim" : 768,
      "pruned_heads": {},
      "remove_invalid_values": false,
      "repetition_penalty": 1.0,
      "return_dict": true,
      "return_dict_in_generate": false,
      "sep_token_id": null,
      "task_specific_params": null,
      "temperature": 1.0,
      "tie_encoder_decoder": false,
      "tie_word_embeddings": true,
      "tokenizer_class": null,
      "top_k": 50,
      "top_p": 1.0,
      "torch_dtype": null,
      "torchscript": false,
      "transformers_version": "4.16.0.dev0",
      "use_bfloat16": false
    },
    "text_config": {
      "architectures": [
        "LlamaForCausalLM"
      ],
      "bos_token_id": 1,
      "eos_token_id": 2,
      "hidden_act": "silu",
      "hidden_size": 4096,
      "initializer_range": 0.02,
      "intermediate_size": 11008,
      "max_position_embeddings": 2048,
      "model_type": "llama",
      "num_attention_heads": 32,
      "num_hidden_layers": 32,
      "pad_token_id": 0,
      "rms_norm_eps": 1e-06,
      "tie_word_embeddings": false,
      "torch_dtype": "float16",
      "transformers_version": "4.30.1",
      "use_cache": true,
      "vocab_size": 49958
    },
    "image_size": 224,
    "use_visual_resampler": true,
    "visual_resampler_config": {
      "num_query_tokens": 64,
      "num_hidden_layers": 6,
      "hidden_size": 1024,
      "num_attention_heads": 16,
      "intermediate_size": 4096
    },
    "tie_word_embeddings": false,
    "vocab_size": 49958
}