config.json

{
  "_name_or_path": "/home/patrickwu/new_datasetvqa/datasetvqa_latest/checkpoints/MIRAGE_llava_llama3_qformer_final_20240929",
  "architectures": [
    "LlavaLlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": [
    128001,
    128008,
    128009
  ],
  "freeze_mm_mlp_adapter": false,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "image_aspect_ratio": "pad",
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "mm_hidden_size": 1024,
  "mm_patch_merge_type": "flat",
  "mm_projector_lr": 2e-05,
  "mm_projector_type": "mlp2x_gelu",
  "mm_qformer": true,
  "mm_reduce_token_method": "qformer_query_aware",
  "mm_retriever": true,
  "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": "llava_llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "qformer_encoder_hidden_size": 1024,
  "qformer_hidden_size": 1024,
  "qformer_intermediate_size": 1024,
  "qformer_max_position_embeddings": 1024,
  "qformer_num_attn_heads": 12,
  "qformer_num_layers": 4,
  "qformer_num_query_tokens": 32,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 8.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "tokenizer_model_max_length": 2048,
  "tokenizer_padding_side": "right",
  "torch_dtype": "float16",
  "transformers_version": "4.43.1",
  "tune_mm_mlp_adapter": false,
  "use_cache": true,
  "use_mm_proj": true,
  "vocab_size": 128256
}