| { |
| "_name_or_path": "Pragformer/PragFormer", |
| "architectures": [ |
| "BERT_Arch" |
| ], |
| "auto_map": { |
| "AutoConfig": "model_config.PragFormerConfig", |
| "AutoModel": "model.BERT_Arch" |
| }, |
| "bert": { |
| "_commit_hash": "43cf2d48e8c75d255dccab2a19e40d4774fd8853", |
| "_name_or_path": "NTUYG/DeepSCC-RoBERTa", |
| "add_cross_attention": false, |
| "architectures": [ |
| "RobertaForSequenceClassification" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "bad_words_ids": null, |
| "begin_suppress_tokens": null, |
| "bos_token_id": 0, |
| "chunk_size_feed_forward": 0, |
| "classifier_dropout": null, |
| "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": 2, |
| "exponential_decay_length_penalty": null, |
| "finetuning_task": null, |
| "forced_bos_token_id": null, |
| "forced_eos_token_id": null, |
| "gradient_checkpointing": false, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 768, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1", |
| "10": "LABEL_10", |
| "11": "LABEL_11", |
| "12": "LABEL_12", |
| "13": "LABEL_13", |
| "14": "LABEL_14", |
| "15": "LABEL_15", |
| "16": "LABEL_16", |
| "17": "LABEL_17", |
| "18": "LABEL_18", |
| "2": "LABEL_2", |
| "3": "LABEL_3", |
| "4": "LABEL_4", |
| "5": "LABEL_5", |
| "6": "LABEL_6", |
| "7": "LABEL_7", |
| "8": "LABEL_8", |
| "9": "LABEL_9" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1, |
| "LABEL_10": 10, |
| "LABEL_11": 11, |
| "LABEL_12": 12, |
| "LABEL_13": 13, |
| "LABEL_14": 14, |
| "LABEL_15": 15, |
| "LABEL_16": 16, |
| "LABEL_17": 17, |
| "LABEL_18": 18, |
| "LABEL_2": 2, |
| "LABEL_3": 3, |
| "LABEL_4": 4, |
| "LABEL_5": 5, |
| "LABEL_6": 6, |
| "LABEL_7": 7, |
| "LABEL_8": 8, |
| "LABEL_9": 9 |
| }, |
| "layer_norm_eps": 1e-05, |
| "length_penalty": 1.0, |
| "max_length": 20, |
| "max_position_embeddings": 514, |
| "min_length": 0, |
| "model_type": "roberta", |
| "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": 1, |
| "position_embedding_type": "absolute", |
| "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": "4.2.0", |
| "type_vocab_size": 1, |
| "typical_p": 1.0, |
| "use_bfloat16": false, |
| "use_cache": true, |
| "vocab_size": 50265 |
| }, |
| "dropout": 0.2, |
| "fc1": 512, |
| "fc2": 2, |
| "model_type": "pragformer_reduction", |
| "softmax_dim": 1, |
| "torch_dtype": "float32", |
| "transformers_version": "4.25.1" |
| } |
|
|
