config.json

{
  "X": [
    "VIDEO",
    "IMAGE"
  ],
  "_name_or_path": "./checkpoints/llava-v1.5-7b",
  "architectures": [
    "LlavaLlamaForCausalLMRMT"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "freeze_mm_mlp_adapter": false,
  "freeze_mm_vision_resampler": false,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "image_aspect_ratio": "pad",
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_length": 4096,
  "max_position_embeddings": 4096,
  "mm_attention_probs_dropout_prob": 0.1,
  "mm_hidden_act": "gelu",
  "mm_hidden_dropout_prob": 0.1,
  "mm_hidden_size": 1024,
  "mm_image_tower": "./checkpoints/LanguageBind_Image",
  "mm_intermediate_size": 4096,
  "mm_layer_norm_eps": 1e-12,
  "mm_num_attention_heads": 8,
  "mm_patch_merge_type": "flat",
  "mm_projector_lr": null,
  "mm_projector_type": "rmt_r_transformer1x",
  "mm_resampler_type": null,
  "mm_use_im_patch_token": false,
  "mm_use_im_start_end": false,
  "mm_use_x_patch_token": false,
  "mm_use_x_start_end": false,
  "mm_video_tower": "./checkpoints/LanguageBind_Video_merge",
  "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_frames": 16,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "tokenizer_model_max_length": 2048,
  "tokenizer_padding_side": "right",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.39.1",
  "tune_mm_mlp_adapter": false,
  "tune_mm_vision_resampler": false,
  "unfreeze_mm_vision_tower": false,
  "use_cache": true,
  "use_mm_proj": true,
  "vocab_size": 32000
}