abhi11nav/codebert-gpt2-commitgen

1{2  "_commit_hash": null,3  "architectures": [4    "EncoderDecoderModel"5  ],6  "decoder": {7    "_name_or_path": "gpt2",8    "activation_function": "gelu_new",9    "add_cross_attention": true,10    "architectures": [11      "GPT2LMHeadModel"12    ],13    "attn_pdrop": 0.1,14    "bad_words_ids": null,15    "begin_suppress_tokens": null,16    "bos_token_id": 50256,17    "chunk_size_feed_forward": 0,18    "cross_attention_hidden_size": null,19    "decoder_start_token_id": null,20    "diversity_penalty": 0.0,21    "do_sample": false,22    "early_stopping": false,23    "embd_pdrop": 0.1,24    "encoder_no_repeat_ngram_size": 0,25    "eos_token_id": 50256,26    "exponential_decay_length_penalty": null,27    "finetuning_task": null,28    "forced_bos_token_id": null,29    "forced_eos_token_id": null,30    "id2label": {31      "0": "LABEL_0",32      "1": "LABEL_1"33    },34    "initializer_range": 0.02,35    "is_decoder": true,36    "is_encoder_decoder": false,37    "label2id": {38      "LABEL_0": 0,39      "LABEL_1": 140    },41    "layer_norm_epsilon": 1e-05,42    "length_penalty": 1.0,43    "max_length": 20,44    "min_length": 0,45    "model_type": "gpt2",46    "n_ctx": 1024,47    "n_embd": 768,48    "n_head": 12,49    "n_inner": null,50    "n_layer": 12,51    "n_positions": 1024,52    "no_repeat_ngram_size": 0,53    "num_beam_groups": 1,54    "num_beams": 1,55    "num_return_sequences": 1,56    "output_attentions": false,57    "output_hidden_states": false,58    "output_scores": false,59    "pad_token_id": null,60    "prefix": null,61    "problem_type": null,62    "pruned_heads": {},63    "remove_invalid_values": false,64    "reorder_and_upcast_attn": false,65    "repetition_penalty": 1.0,66    "resid_pdrop": 0.1,67    "return_dict": true,68    "return_dict_in_generate": false,69    "scale_attn_by_inverse_layer_idx": false,70    "scale_attn_weights": true,71    "sep_token_id": null,72    "summary_activation": null,73    "summary_first_dropout": 0.1,74    "summary_proj_to_labels": true,75    "summary_type": "cls_index",76    "summary_use_proj": true,77    "suppress_tokens": null,78    "task_specific_params": {79      "text-generation": {80        "do_sample": true,81        "max_length": 5082      }83    },84    "temperature": 1.0,85    "tf_legacy_loss": false,86    "tie_encoder_decoder": false,87    "tie_word_embeddings": true,88    "tokenizer_class": null,89    "top_k": 50,90    "top_p": 1.0,91    "torch_dtype": null,92    "torchscript": false,93    "transformers_version": "4.25.1",94    "typical_p": 1.0,95    "use_bfloat16": false,96    "use_cache": true,97    "vocab_size": 5025798  },99  "decoder_start_token_id": 0,100  "early_stopping": true,101  "encoder": {102    "_name_or_path": "microsoft/codebert-base",103    "add_cross_attention": false,104    "architectures": [105      "RobertaModel"106    ],107    "attention_probs_dropout_prob": 0.1,108    "bad_words_ids": null,109    "begin_suppress_tokens": null,110    "bos_token_id": 0,111    "chunk_size_feed_forward": 0,112    "classifier_dropout": null,113    "cross_attention_hidden_size": null,114    "decoder_start_token_id": null,115    "diversity_penalty": 0.0,116    "do_sample": false,117    "early_stopping": false,118    "encoder_no_repeat_ngram_size": 0,119    "eos_token_id": 2,120    "exponential_decay_length_penalty": null,121    "finetuning_task": null,122    "forced_bos_token_id": null,123    "forced_eos_token_id": null,124    "hidden_act": "gelu",125    "hidden_dropout_prob": 0.1,126    "hidden_size": 768,127    "id2label": {128      "0": "LABEL_0",129      "1": "LABEL_1"130    },131    "initializer_range": 0.02,132    "intermediate_size": 3072,133    "is_decoder": false,134    "is_encoder_decoder": false,135    "label2id": {136      "LABEL_0": 0,137      "LABEL_1": 1138    },139    "layer_norm_eps": 1e-05,140    "length_penalty": 1.0,141    "max_length": 20,142    "max_position_embeddings": 514,143    "min_length": 0,144    "model_type": "roberta",145    "no_repeat_ngram_size": 0,146    "num_attention_heads": 12,147    "num_beam_groups": 1,148    "num_beams": 1,149    "num_hidden_layers": 12,150    "num_return_sequences": 1,151    "output_attentions": false,152    "output_hidden_states": false,153    "output_past": true,154    "output_scores": false,155    "pad_token_id": 1,156    "position_embedding_type": "absolute",157    "prefix": null,158    "problem_type": null,159    "pruned_heads": {},160    "remove_invalid_values": false,161    "repetition_penalty": 1.0,162    "return_dict": true,163    "return_dict_in_generate": false,164    "sep_token_id": null,165    "suppress_tokens": null,166    "task_specific_params": null,167    "temperature": 1.0,168    "tf_legacy_loss": false,169    "tie_encoder_decoder": false,170    "tie_word_embeddings": true,171    "tokenizer_class": null,172    "top_k": 50,173    "top_p": 1.0,174    "torch_dtype": null,175    "torchscript": false,176    "transformers_version": "4.25.1",177    "type_vocab_size": 1,178    "typical_p": 1.0,179    "use_bfloat16": false,180    "use_cache": true,181    "vocab_size": 50265182  },183  "eos_token_id": 2,184  "is_encoder_decoder": true,185  "length_penalty": 2.0,186  "max_length": 64,187  "min_length": 5,188  "model_type": "encoder-decoder",189  "no_repeat_ngram_size": 3,190  "num_beams": 4,191  "pad_token_id": 1,192  "torch_dtype": "float32",193  "transformers_version": null,194  "vocab_size": 50257195}196