config.json

{
  "_name_or_path": "/workspace/volume/yq-data/demos/checkpoints/text_and_image_and_pose_data_mistral_finetuning_fp16",
  "architectures": [
    "PoseLlavaForCausalLM"
  ],
  "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",
  "image_crop_resolution": 224,
  "image_grid_pinpoints": [
    [
      336,
      672
    ],
    [
      672,
      336
    ],
    [
      672,
      672
    ],
    [
      1008,
      336
    ],
    [
      336,
      1008
    ]
  ],
  "image_split_resolution": 224,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 32768,
  "mm_hidden_size": 1024,
  "mm_patch_merge_type": "flat",
  "mm_projector_lr": 1e-05,
  "mm_projector_type": "mlp2x_gelu",
  "mm_resampler_type": null,
  "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": "/workspace/volume/yq-data/datasets/pretrain_models/mistral_clip-vit-large-patch14-336-fp16",
  "mm_vision_tower_lr": 2e-06,
  "model_type": "posellava",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pad_token": "<unk>",
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "tokenizer_model_max_length": 2048,
  "tokenizer_padding_side": "right",
  "torch_dtype": "float16",
  "transformers_version": "4.40.0",
  "tune_entire_model": false,
  "tune_mm_mlp_adapter": false,
  "tune_mm_vision_resampler": false,
  "tune_vision_tower": false,
  "unfreeze_mm_vision_tower": true,
  "use_cache": true,
  "use_mm_proj": true,
  "vocab_size": 32002
}