{
  "architectures": [
    "VLV_MODEL"
  ],
  "auto_map": {
    "AutoConfig": "configuration_vlv.VLV_Config",
    "AutoModel": "VLV_stage2.VLV_MODEL",
    "AutoModelForCausalLM": "VLV_stage2.VLV_MODEL"
  },
  "model_type": "VLV_decoder",
  "batch_size": 1,
  "deepspeed": true,
  "distributed": true,
  "fp32": true,
  "guidance_scale": 2.5,
  "hidden_size": 128,
  "image_size": 384,
  "learnable_token_length": 77,
  "local_rank": 0,
  "mixed_precision": "fp32",
  "num_inference_steps": 50,
  "torch_dtype": "float32",
  "transformers_version": "4.51.1",
  "use_text_encoder": true,
  "verbose": true,
  "qwen_model": "Qwen/Qwen2.5-3B",
  "stable_diffusion_model_path": "stabilityai/stable-diffusion-2-1-base",
  "florence2_model_path": "microsoft/Florence-2-large",
  "max_length": 300,
  "num_beams": 4,
  "qwen2_config":{
    "architectures": [
      "Qwen2ForCausalLM"
    ],
    "attention_dropout": 0.0,
    "bos_token_id": 151643,
    "eos_token_id": 151643,
    "hidden_act": "silu",
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 11008,
    "max_position_embeddings": 32768,
    "max_window_layers": 36,
    "model_type": "qwen2",
    "num_attention_heads": 16,
    "num_hidden_layers": 36,
    "num_key_value_heads": 2,
    "rms_norm_eps": 1e-06,
    "rope_theta": 1000000.0,
    "sliding_window": 32768,
    "tie_word_embeddings": true,
    "torch_dtype": "float32",
    "transformers_version": "4.40.1",
    "use_cache": true,
    "use_mrope": false,
    "use_sliding_window": false,
    "vocab_size": 151936
  }  
}