{
  "_name_or_path": "./final_model",
  "architectures": [
    "Blip2ForConditionalGeneration"
  ],
  "initializer_factor": 1.0,
  "initializer_range": 0.02,
  "model_type": "blip-2",
  "num_query_tokens": 32,
  "pad_token_id": 0,
  "qformer_config": {
    "classifier_dropout": null,
    "model_type": "blip_2_qformer"
  },
  "text_config": {
    "_name_or_path": "SeaLLMs/SeaLLM-7B-v2.5",
    "architectures": [
      "GemmaForCausalLM"
    ],
    "attention_bias": false,
    "eos_token_id": 1,
    "head_dim": 256,
    "hidden_act": "gelu",
    "hidden_activation": null,
    "hidden_size": 3072,
    "initializer_range": 0.02,
    "intermediate_size": 24576,
    "max_position_embeddings": 8192,
    "model_type": "gemma",
    "num_attention_heads": 16,
    "num_hidden_layers": 28,
    "num_key_value_heads": 16,
    "pad_token_id": 0,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 10000.0,
    "torch_dtype": "bfloat16",
    "vocab_size": 256000
  },
  "torch_dtype": "float32",
  "transformers_version": "4.40.1",
  "use_decoder_only_language_model": true,
  "vision_config": {
    "dropout": 0.0,
    "image_size": 364,
    "initializer_factor": 1.0,
    "model_type": "blip_2_vision_model",
    "num_channels": 3,
    "projection_dim": 512
  }
}