config.json

{
  "model_type": "mplug_owl2_1",
  "multiway": true,
  "attn_dropout_prob": 0.0,
  "bf16": false,
  "emb_dropout_prob": 0.0,
  "fp16": false,
  "fp32": false,
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 22016,
  "kv_channels": 128,
  "layer_norm_epsilon": 1e-06,
  "max_position_embeddings": 8192,
  "no_bias": true,
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "onnx_safe": null,
  "rotary_emb_base": 10000,
  "rotary_pct": 1.0,
  "scale_attn_weights": true,
  "seq_length": 2048,
  "tie_word_embeddings": false,
  "tokenizer_type": "QWenTokenizer",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.31.0",
  "use_cache": true,
  "use_dynamic_ntk": true,
  "use_flash_attn": false,
  "use_logn_attn": true,
  "visual_config": {
    "visual_abstractor": {
      "_name_or_path": "",
      "use_cls_token": false,
      "add_cross_attention": false,
      "architectures": null,
      "attention_probs_dropout_prob": 0.0,
      "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_hidden_size": 1664,
      "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,
      "grid_size": 32,
      "hidden_size": 1664,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "initializer_range": 0.02,
      "intermediate_size": 5632,
      "is_decoder": false,
      "is_encoder_decoder": false,
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "layer_norm_eps": 1e-06,
      "length_penalty": 1.0,
      "max_length": 20,
      "min_length": 0,
      "model_type": "mplug_owl_visual_abstract",
      "no_repeat_ngram_size": 0,
      "num_attention_heads": 16,
      "num_beam_groups": 1,
      "num_beams": 1,
      "num_hidden_layers": 6,
      "num_learnable_queries": 64,
      "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,
      "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": null,
      "torchscript": false,
      "transformers_version": "4.28.1",
      "typical_p": 1.0,
      "use_bfloat16": false
    },
    "visual_model": {
      "_name_or_path": "",
      "use_cls_token": false,
      "use_post_layernorm": false,
      "add_cross_attention": false,
      "architectures": null,
      "attention_dropout": 0.0,
      "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_act": "gelu",
      "hidden_size": 1664,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "image_size": 448,
      "initializer_factor": 1.0,
      "initializer_range": 0.02,
      "intermediate_size": 8192,
      "is_decoder": false,
      "is_encoder_decoder": false,
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "layer_norm_eps": 1e-06,
      "length_penalty": 1.0,
      "max_length": 20,
      "min_length": 0,
      "model_type": "mplug_owl_vision_model",
      "no_repeat_ngram_size": 0,
      "num_attention_heads": 16,
      "num_beam_groups": 1,
      "num_beams": 1,
      "num_channels": 3,
      "num_hidden_layers": 48,
      "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_dim": 768,
      "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,
      "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": null,
      "torchscript": false,
      "transformers_version": "4.28.1",
      "typical_p": 1.0,
      "use_bfloat16": false,
      "use_flash_attn": false
    }
  },
  "vocab_size": 151936
}