{
  "architectures": [
    "LlavaLlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "condition_max_length": 128,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "freeze_mm_mlp_adapter": false,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "image_aspect_ratio": "pad",
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "lm_hidden_size": 4096,
  "loop_deep_sup_weight": null,
  "loop_draft_max_new_tokens": 16,
  "loop_edm2_logvar_init": 0.0,
  "loop_end": null,
  "loop_eval_steps": 0,
  "loop_fused_readout": false,
  "loop_mode": "none",
  "loop_prefix_deep_sup": false,
  "loop_readout_mode": "last",
  "loop_start": null,
  "loop_step_embed": "sinusoidal",
  "loop_steps": 3,
  "loop_tbptt_segment": 1,
  "loop_traj_deep_sup": false,
  "loop_traj_text": false,
  "loop_truncated_bptt": false,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "mm_hidden_size": 1024,
  "mm_patch_merge_type": "flat",
  "mm_projector_lr": 5e-05,
  "mm_projector_type": "mlp2x_gelu",
  "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": 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",
  "transformers_version": "4.57.6",
  "tune_mm_mlp_adapter": false,
  "use_cache": true,
  "use_mm_proj": true,
  "vision_input_res": 448,
  "vision_spatial_pool": 2,
  "vocab_size": 32000
}