configuration_clipcap.py

from transformers import PretrainedConfig, AutoConfig


class CLIPEncoderDecoderConfig(PretrainedConfig):
    model_type = "clip-encoder-decoder"

    def __init__(
        self, 
        decoder={'_name_or_path': '',
 'activation_function': 'gelu_new',
 'add_cross_attention': True,
 'architectures': ['GPT2LMHeadModel'],
 'attn_pdrop': 0.1,
 'bad_words_ids': None,
 'begin_suppress_tokens': None,
 'bos_token_id': 50256,
 'chunk_size_feed_forward': 0,
 'cross_attention_hidden_size': None,
 'decoder_start_token_id': None,
 'diversity_penalty': 0.0,
 'do_sample': False,
 'early_stopping': False,
 'embd_pdrop': 0.1,
 'encoder_no_repeat_ngram_size': 0,
 'eos_token_id': 50256,
 'exponential_decay_length_penalty': None,
 'finetuning_task': None,
 'forced_bos_token_id': None,
 'forced_eos_token_id': None,
 'id2label': {'0': 'LABEL_0', '1': 'LABEL_1'},
 'initializer_range': 0.02,
 'is_decoder': True,
 'is_encoder_decoder': False,
 'label2id': {'LABEL_0': 0, 'LABEL_1': 1},
 'layer_norm_epsilon': 1e-05,
 'length_penalty': 1.0,
 'max_length': 20,
 'min_length': 0,
 'model_type': 'gpt2',
 'n_ctx': 1024,
 'n_embd': 768,
 'n_head': 12,
 'n_inner': None,
 'n_layer': 12,
 'n_positions': 1024,
 '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': None,
 'prefix': None,
 'problem_type': None,
 'pruned_heads': {},
 'remove_invalid_values': False,
 'reorder_and_upcast_attn': False,
 'repetition_penalty': 1.0,
 'resid_pdrop': 0.1,
 'return_dict': True,
 'return_dict_in_generate': False,
 'scale_attn_by_inverse_layer_idx': False,
 'scale_attn_weights': True,
 'sep_token_id': None,
 'summary_activation': None,
 'summary_first_dropout': 0.1,
 'summary_proj_to_labels': True,
 'summary_type': 'cls_index',
 'summary_use_proj': True,
 'suppress_tokens': None,
 'task_specific_params': {'text-generation': {'do_sample': True,
   'max_length': 50}},
 'temperature': 1.0,
 'tf_legacy_loss': False,
 'tie_encoder_decoder': False,
 'tie_word_embeddings': True,
 'tokenizer_class': None,
 'top_k': 50,
 'top_p': 1.0,
 'torch_dtype': None,
 'torchscript': False,
 'typical_p': 1.0,
 'use_bfloat16': False,
 'use_cache': True,
 'vocab_size': 50257}, 
        **kwargs):
        super().__init__(**kwargs)

        self.decoder = AutoConfig.for_model(**decoder)
        self.is_encoder_decoder = True

    @classmethod
    def from_encoder_decoder_configs(
            cls, encoder_config: PretrainedConfig, decoder_config: PretrainedConfig, **kwargs
    ) -> PretrainedConfig:
        r"""
        Instantiate a [`VisionEncoderDecoderConfig`] (or a derived class) from a pre-trained encoder model
        configuration and decoder model configuration.

        Returns:
            [`VisionEncoderDecoderConfig`]: An instance of a configuration object
        """
        decoder_config.is_decoder = True
        decoder_config.add_cross_attention = True

        return cls(encoder=encoder_config.to_dict(), decoder=decoder_config.to_dict(), **kwargs)