config.json

{
  "architectures": [
    "SliMMForConditionalGeneration"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "custom_visual_model": "menglc/DFN-Huge-Qwen2VL-7B",
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 896,
  "image_token_id": 151655,
  "initializer_range": 0.02,
  "intermediate_size": 4864,
  "max_position_embeddings": 32768,
  "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
  "model_type": "qwen2",
  "num_attention_heads": 14,
  "num_hidden_layers": 24,
  "num_key_value_heads": 2,
  "pos_skipping_range": 4096,
  "rms_norm_eps": 1e-06,
  "rope_scaling": {
    "mrope_section": [
      8,
      12,
      12
    ],
    "rope_type": "default",
    "type": "default"
  },
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.47.0.dev0",
  "use_cache": true,
  "use_deepstack": false,
  "use_mrope": true,
  "use_pos_skipping": false,
  "use_sliding_window": false,
  "video_token_id": 151656,
  "vision_end_token_id": 151653,
  "vision_start_token_id": 151652,
  "vision_token_id": 151654,
  "vocab_size": 151657
}