{
  "architectures": [
    "PerceiverForImageClassificationFourier","SeamlessM4Tv2ForTextToText","XXXForTextToText","DeepseekV3ForCausalLM"
  ],
  "auto_map": {},
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 8192,
  "initializer_range": 0.02,
  "intermediate_size": 29568,
  "max_position_embeddings": 32768,
  "max_window_layers": 70,
  "model_type": "xxx",
  "num_attention_heads": 64,
  "num_hidden_layers": 80,
  "num_key_value_heads": 8,
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "sliding_window": 131072,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.43.1",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 152064,
  "vision_config": {
    "depth": 32,
    "hidden_act": "silu",
    "hidden_size": 1280,
    "intermediate_size": 3420,
    "num_heads": 16,
    "in_chans": 3,
    "out_hidden_size": 3584,
    "patch_size": 14,
    "spatial_merge_size": 2,
    "spatial_patch_size": 14,
    "window_size": 112,
    "fullatt_block_indexes": [
      7,
      15,
      23,
      31
    ],
    "tokens_per_second": 2,
    "temporal_patch_size": 2
  },
  "rope_scaling": {
    "type": "mrope",
    "mrope_section": [
      16,
      24,
      24
    ]
  }
}