config.json

{
  "_name_or_path": "./output_llava/checkpoints/pretrain-conv-llava-jp-1.3b-stage1-768",
  "activation_function": "gelu",
  "architectures": [
    "LlavaGpt2ForCausalLM"
  ],
  "attn_pdrop": 0.1,
  "bos_token_id": 7,
  "drop_path_rates": [
    0.085,
    0.088,
    0.091,
    0.094,
    0.097,
    0.1
  ],
  "embd_pdrop": 0.1,
  "eos_token_id": 7,
  "gradient_checkpointing": false,
  "image_aspect_ratio": "square",
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "mm_hidden_size": 3072,
  "mm_projector_type": "mlp2x_gelu",
  "mm_vision_resolution": 768,
  "mm_vision_select_feature": "patch",
  "mm_vision_select_layer": -2,
  "mm_vision_tower": "convnext_large",
  "model_type": "llava-jp",
  "n_ctx": 1024,
  "n_embd": 2048,
  "n_head": 16,
  "n_inner": 8192,
  "n_layer": 24,
  "n_positions": 2048,
  "reorder_and_upcast_attn": false,
  "resid_pdrop": 0.1,
  "scale_attn_by_inverse_layer_idx": false,
  "scale_attn_weights": true,
  "scales": null,
  "summary_activation": null,
  "summary_first_dropout": 0.1,
  "summary_proj_to_labels": true,
  "summary_type": "cls_index",
  "summary_use_proj": true,
  "tokenizer_model_max_length": 1532,
  "tokenizer_padding_side": "right",
  "torch_dtype": "float32",
  "transformers_version": "4.38.2",
  "tune_mm_mlp_adapter": false,
  "use_cache": true,
  "use_mm_proj": true,
  "vision_add_five_stage": 6,
  "vision_encoder_type": "ConvNeXt",
  "vision_five_stage_width": 3072,
  "vocab_size": 50688
}