{
  "architectures": [
    "Ovis"
  ],
  "auto_map": {
    "AutoConfig": "configuration_ovis.OvisConfig",
    "AutoModelForCausalLM": "modeling_ovis.Ovis"
  },
  "conversation_formatter_class": "QwenConversationFormatter",
  "disable_tie_weight": false,
  "hidden_size": 5120,
  "llm_attn_implementation": "flash_attention_2",
  "llm_config": {
    "_attn_implementation_autoset": true,
    "_name_or_path": "Qwen/Qwen2.5-14B-Instruct",
    "add_cross_attention": false,
    "architectures": [
      "Qwen2ForCausalLM"
    ],
    "attention_dropout": 0.0,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 151643,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 151645,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_act": "silu",
    "hidden_size": 5120,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 13824,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 32768,
    "max_window_layers": 70,
    "min_length": 0,
    "model_type": "qwen2",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 40,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 48,
    "num_key_value_heads": 8,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 1000000.0,
    "sep_token_id": null,
    "sliding_window": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": false,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": "bfloat16",
    "torchscript": false,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true,
    "use_sliding_window": false,
    "vocab_size": 152064
  },
  "model_type": "ovis",
  "multimodal_max_length": 32768,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.46.2",
  "use_cache": true,
  "visual_tokenizer_config": {
    "_attn_implementation_autoset": true,
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": null,
    "backbone_config": {
      "_attn_implementation_autoset": true,
      "_name_or_path": "apple/aimv2-huge-patch14-448",
      "add_cross_attention": false,
      "architectures": [
        "AIMv2Model"
      ],
      "attention_dropout": 0.0,
      "auto_map": {
        "AutoConfig": "configuration_aimv2.AIMv2Config",
        "AutoModel": "modeling_aimv2.AIMv2Model",
        "FlaxAutoModel": "modeling_flax_aimv2.FlaxAIMv2Model"
      },
      "bad_words_ids": null,
      "begin_suppress_tokens": null,
      "bos_token_id": null,
      "chunk_size_feed_forward": 0,
      "cross_attention_hidden_size": null,
      "decoder_start_token_id": null,
      "diversity_penalty": 0.0,
      "do_sample": false,
      "early_stopping": false,
      "encoder_no_repeat_ngram_size": 0,
      "eos_token_id": null,
      "exponential_decay_length_penalty": null,
      "finetuning_task": null,
      "forced_bos_token_id": null,
      "forced_eos_token_id": null,
      "hidden_size": 1536,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "image_size": 448,
      "intermediate_size": 4096,
      "is_decoder": false,
      "is_encoder_decoder": false,
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "length_penalty": 1.0,
      "max_length": 20,
      "min_length": 0,
      "model_type": "aimv2",
      "no_repeat_ngram_size": 0,
      "num_attention_heads": 12,
      "num_beam_groups": 1,
      "num_beams": 1,
      "num_channels": 3,
      "num_hidden_layers": 24,
      "num_return_sequences": 1,
      "output_attentions": false,
      "output_hidden_states": false,
      "output_scores": false,
      "pad_token_id": null,
      "patch_size": 14,
      "prefix": null,
      "problem_type": null,
      "projection_dropout": 0.0,
      "pruned_heads": {},
      "qkv_bias": false,
      "remove_invalid_values": false,
      "repetition_penalty": 1.0,
      "return_dict": true,
      "return_dict_in_generate": false,
      "rms_norm_eps": 1e-05,
      "sep_token_id": null,
      "suppress_tokens": null,
      "task_specific_params": null,
      "temperature": 1.0,
      "tf_legacy_loss": false,
      "tie_encoder_decoder": false,
      "tie_word_embeddings": true,
      "tokenizer_class": null,
      "top_k": 50,
      "top_p": 1.0,
      "torch_dtype": "bfloat16",
      "torchscript": false,
      "typical_p": 1.0,
      "use_bfloat16": false,
      "use_bias": false
    },
    "backbone_kwargs": {},
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "depths": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "drop_cls_token": false,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": null,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_stride": 2,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "model_type": "aimv2_visual_tokenizer",
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "tau": 1.0,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenize_function": "softmax",
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_indicators": false,
    "vocab_size": 65536
  }
}