ckpt/ckpt-49499/config.json

{
  "architectures": [
    "CLIPVisionMBartForConditionalGeneration"
  ],
  "clip_vision_config": {
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": [
      "CLIPModel"
    ],
    "attention_dropout": 0.0,
    "bad_words_ids": null,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "dropout": 0.0,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "gradient_checkpointing": false,
    "hidden_act": "quick_gelu",
    "hidden_size": 768,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "image_size": 224,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-05,
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "model_type": "clip_vision_model",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 12,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 12,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "patch_size": 32,
    "prefix": null,
    "problem_type": null,
    "projection_dim": 512,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "text_config": {
      "_name_or_path": "",
      "add_cross_attention": false,
      "architectures": null,
      "attention_dropout": 0.0,
      "bad_words_ids": null,
      "bos_token_id": 0,
      "chunk_size_feed_forward": 0,
      "decoder_start_token_id": null,
      "diversity_penalty": 0.0,
      "do_sample": false,
      "dropout": 0.0,
      "early_stopping": false,
      "encoder_no_repeat_ngram_size": 0,
      "eos_token_id": 2,
      "finetuning_task": null,
      "forced_bos_token_id": null,
      "forced_eos_token_id": null,
      "gradient_checkpointing": false,
      "hidden_act": "quick_gelu",
      "hidden_size": 512,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "initializer_factor": 1.0,
      "initializer_range": 0.02,
      "intermediate_size": 2048,
      "is_decoder": false,
      "is_encoder_decoder": false,
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "layer_norm_eps": 1e-05,
      "length_penalty": 1.0,
      "max_length": 20,
      "max_position_embeddings": 77,
      "min_length": 0,
      "model_type": "clip_text_model",
      "no_repeat_ngram_size": 0,
      "num_attention_heads": 8,
      "num_beam_groups": 1,
      "num_beams": 1,
      "num_hidden_layers": 12,
      "num_return_sequences": 1,
      "output_attentions": false,
      "output_hidden_states": false,
      "output_scores": false,
      "pad_token_id": 1,
      "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,
      "task_specific_params": null,
      "temperature": 1.0,
      "tie_encoder_decoder": false,
      "tie_word_embeddings": true,
      "tokenizer_class": null,
      "top_k": 50,
      "top_p": 1.0,
      "torchscript": false,
      "transformers_version": "4.7.0.dev0",
      "use_bfloat16": false,
      "vocab_size": 49408
    },
    "text_config_dict": null,
    "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": "4.9.0.dev0",
    "use_bfloat16": false,
    "vision_config": {
      "_name_or_path": "",
      "add_cross_attention": false,
      "architectures": null,
      "attention_dropout": 0.0,
      "bad_words_ids": null,
      "bos_token_id": null,
      "chunk_size_feed_forward": 0,
      "decoder_start_token_id": null,
      "diversity_penalty": 0.0,
      "do_sample": false,
      "dropout": 0.0,
      "early_stopping": false,
      "encoder_no_repeat_ngram_size": 0,
      "eos_token_id": null,
      "finetuning_task": null,
      "forced_bos_token_id": null,
      "forced_eos_token_id": null,
      "gradient_checkpointing": false,
      "hidden_act": "quick_gelu",
      "hidden_size": 768,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "image_size": 224,
      "initializer_factor": 1.0,
      "initializer_range": 0.02,
      "intermediate_size": 3072,
      "is_decoder": false,
      "is_encoder_decoder": false,
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "layer_norm_eps": 1e-05,
      "length_penalty": 1.0,
      "max_length": 20,
      "min_length": 0,
      "model_type": "clip_vision_model",
      "no_repeat_ngram_size": 0,
      "num_attention_heads": 12,
      "num_beam_groups": 1,
      "num_beams": 1,
      "num_hidden_layers": 12,
      "num_return_sequences": 1,
      "output_attentions": false,
      "output_hidden_states": false,
      "output_scores": false,
      "pad_token_id": null,
      "patch_size": 32,
      "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,
      "task_specific_params": null,
      "temperature": 1.0,
      "tie_encoder_decoder": false,
      "tie_word_embeddings": true,
      "tokenizer_class": null,
      "top_k": 50,
      "top_p": 1.0,
      "torchscript": false,
      "transformers_version": "4.7.0.dev0",
      "use_bfloat16": false
    },
    "vision_config_dict": null
  },
  "is_encoder_decoder": true,
  "mbart_config": {
    "_name_or_path": "/home/suraj/projects/mbart-50/hf_models/mbart-50-large",
    "_num_labels": 3,
    "activation_dropout": 0.0,
    "activation_function": "gelu",
    "add_bias_logits": false,
    "add_cross_attention": false,
    "add_final_layer_norm": true,
    "architectures": [
      "MBartForConditionalGeneration"
    ],
    "attention_dropout": 0.0,
    "bad_words_ids": null,
    "bos_token_id": 0,
    "chunk_size_feed_forward": 0,
    "classif_dropout": 0.0,
    "classifier_dropout": 0.0,
    "d_model": 1024,
    "decoder_attention_heads": 16,
    "decoder_ffn_dim": 4096,
    "decoder_layerdrop": 0.0,
    "decoder_layers": 12,
    "decoder_start_token_id": 2,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "dropout": 0.1,
    "early_stopping": true,
    "encoder_attention_heads": 16,
    "encoder_ffn_dim": 4096,
    "encoder_layerdrop": 0.0,
    "encoder_layers": 12,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 2,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": 2,
    "gradient_checkpointing": false,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1",
      "2": "LABEL_2"
    },
    "init_std": 0.02,
    "is_decoder": false,
    "is_encoder_decoder": true,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1,
      "LABEL_2": 2
    },
    "length_penalty": 1.0,
    "max_length": 200,
    "max_position_embeddings": 1024,
    "min_length": 0,
    "model_type": "mbart",
    "no_repeat_ngram_size": 0,
    "normalize_before": true,
    "normalize_embedding": true,
    "num_beam_groups": 1,
    "num_beams": 5,
    "num_hidden_layers": 12,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_past": true,
    "output_scores": false,
    "pad_token_id": 1,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "scale_embedding": true,
    "sep_token_id": null,
    "static_position_embeddings": false,
    "task_specific_params": null,
    "temperature": 1.0,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": "MBart50Tokenizer",
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "transformers_version": "4.9.0.dev0",
    "use_bfloat16": false,
    "use_cache": true,
    "vocab_size": 250054
  },
  "model_type": "clip-vision-mbart",
  "seed": 42,
  "transformers_version": null
}