CoolFace
Modelpublic

optimum-internal-testing/tiny-random-encoder-decoder-gpt2-bert

sourceHugging Faceupdated 1y agoView on Hugging Face
0likes6.2kdownloads
config.json180 linesDownload Raw Back to root
1{2  "architectures": [3    "EncoderDecoderModel"4  ],5  "decoder": {6    "_name_or_path": "hf-internal-testing/tiny-random-gpt2",7    "activation_function": "gelu_new",8    "add_cross_attention": true,9    "architectures": null,10    "attention_probs_dropout_prob": 0.1,11    "attn_pdrop": 0.1,12    "bad_words_ids": null,13    "begin_suppress_tokens": null,14    "bos_token_id": 98,15    "chunk_size_feed_forward": 0,16    "cross_attention_hidden_size": null,17    "decoder_start_token_id": null,18    "diversity_penalty": 0.0,19    "do_sample": false,20    "early_stopping": false,21    "embd_pdrop": 0.1,22    "encoder_no_repeat_ngram_size": 0,23    "eos_token_id": 98,24    "exponential_decay_length_penalty": null,25    "finetuning_task": null,26    "forced_bos_token_id": null,27    "forced_eos_token_id": null,28    "gradient_checkpointing": false,29    "hidden_act": "gelu",30    "hidden_dropout_prob": 0.1,31    "id2label": {32      "0": "LABEL_0",33      "1": "LABEL_1"34    },35    "initializer_range": 0.02,36    "intermediate_size": 37,37    "is_decoder": true,38    "is_encoder_decoder": false,39    "label2id": {40      "LABEL_0": 0,41      "LABEL_1": 142    },43    "layer_norm_epsilon": 1e-05,44    "length_penalty": 1.0,45    "max_length": 20,46    "min_length": 0,47    "model_type": "gpt2",48    "n_ctx": 512,49    "n_embd": 32,50    "n_head": 4,51    "n_inner": null,52    "n_layer": 5,53    "n_positions": 512,54    "no_repeat_ngram_size": 0,55    "num_beam_groups": 1,56    "num_beams": 1,57    "num_return_sequences": 1,58    "output_attentions": false,59    "output_hidden_states": false,60    "output_scores": false,61    "pad_token_id": 98,62    "prefix": null,63    "problem_type": null,64    "pruned_heads": {},65    "remove_invalid_values": false,66    "reorder_and_upcast_attn": false,67    "repetition_penalty": 1.0,68    "resid_pdrop": 0.1,69    "return_dict": true,70    "return_dict_in_generate": false,71    "scale_attn_by_inverse_layer_idx": false,72    "scale_attn_weights": true,73    "sep_token_id": null,74    "summary_activation": null,75    "summary_first_dropout": 0.1,76    "summary_proj_to_labels": true,77    "summary_type": "cls_index",78    "summary_use_proj": true,79    "suppress_tokens": null,80    "task_specific_params": null,81    "temperature": 1.0,82    "tf_legacy_loss": false,83    "tie_encoder_decoder": false,84    "tie_word_embeddings": true,85    "tokenizer_class": null,86    "top_k": 50,87    "top_p": 1.0,88    "torch_dtype": null,89    "torchscript": false,90    "type_vocab_size": 16,91    "typical_p": 1.0,92    "use_bfloat16": false,93    "use_cache": true,94    "vocab_size": 100095  },96  "encoder": {97    "_name_or_path": "hf-internal-testing/tiny-random-bert",98    "add_cross_attention": false,99    "architectures": null,100    "attention_probs_dropout_prob": 0.1,101    "bad_words_ids": null,102    "begin_suppress_tokens": null,103    "bos_token_id": null,104    "chunk_size_feed_forward": 0,105    "classifier_dropout": null,106    "cross_attention_hidden_size": null,107    "decoder_start_token_id": null,108    "diversity_penalty": 0.0,109    "do_sample": false,110    "early_stopping": false,111    "encoder_no_repeat_ngram_size": 0,112    "eos_token_id": null,113    "exponential_decay_length_penalty": null,114    "finetuning_task": null,115    "forced_bos_token_id": null,116    "forced_eos_token_id": null,117    "gradient_checkpointing": false,118    "hidden_act": "gelu",119    "hidden_dropout_prob": 0.1,120    "hidden_size": 32,121    "id2label": {122      "0": "LABEL_0",123      "1": "LABEL_1"124    },125    "initializer_range": 0.02,126    "intermediate_size": 37,127    "is_decoder": false,128    "is_encoder_decoder": false,129    "label2id": {130      "LABEL_0": 0,131      "LABEL_1": 1132    },133    "layer_norm_eps": 1e-12,134    "length_penalty": 1.0,135    "max_length": 20,136    "max_position_embeddings": 512,137    "min_length": 0,138    "model_type": "bert",139    "no_repeat_ngram_size": 0,140    "num_attention_heads": 4,141    "num_beam_groups": 1,142    "num_beams": 1,143    "num_hidden_layers": 5,144    "num_return_sequences": 1,145    "output_attentions": false,146    "output_hidden_states": false,147    "output_scores": false,148    "pad_token_id": 0,149    "position_embedding_type": "absolute",150    "prefix": null,151    "problem_type": null,152    "pruned_heads": {},153    "remove_invalid_values": false,154    "repetition_penalty": 1.0,155    "return_dict": true,156    "return_dict_in_generate": false,157    "sep_token_id": null,158    "suppress_tokens": null,159    "task_specific_params": null,160    "temperature": 1.0,161    "tf_legacy_loss": false,162    "tie_encoder_decoder": false,163    "tie_word_embeddings": true,164    "tokenizer_class": null,165    "top_k": 50,166    "top_p": 1.0,167    "torch_dtype": null,168    "torchscript": false,169    "type_vocab_size": 16,170    "typical_p": 1.0,171    "use_bfloat16": false,172    "use_cache": true,173    "vocab_size": 1124174  },175  "is_encoder_decoder": true,176  "model_type": "encoder-decoder",177  "torch_dtype": "float32",178  "transformers_version": "4.36.0"179}180 
optimum-internal-testing/tiny-random-encoder-decoder-gpt2-bert · CoolFace