| { |
| "_name_or_path": "cudaizerV2_daebt", |
| "add_cross_attention": true, |
| "architectures": [ |
| "EncoderDecoderModel" |
| ], |
| "decoder": { |
| "_name_or_path": "cudaizerV2_aer", |
| "add_cross_attention": true, |
| "architectures": [ |
| "RobertaForTokenClassification" |
| ], |
| "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": 1536, |
| "id2label": { |
| "0": "O", |
| "1": "B-VAR", |
| "2": "I-VAR", |
| "3": "B-FUNC", |
| "4": "I-FUNC", |
| "5": "B-TYPE", |
| "6": "I-TYPE", |
| "7": "B-PRIM", |
| "8": "I-PRIM", |
| "9": "B-NUM", |
| "10": "I-NUM", |
| "11": "B-POIN", |
| "12": "I-POIN", |
| "13": "B-PDEC", |
| "14": "I-PDEC", |
| "15": "B-CONS", |
| "16": "I-CONS" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 4096, |
| "is_decoder": true, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "B-CONS": 15, |
| "B-FUNC": 3, |
| "B-NUM": 9, |
| "B-PDEC": 13, |
| "B-POIN": 11, |
| "B-PRIM": 7, |
| "B-TYPE": 5, |
| "B-VAR": 1, |
| "I-CONS": 16, |
| "I-FUNC": 4, |
| "I-NUM": 10, |
| "I-PDEC": 14, |
| "I-POIN": 12, |
| "I-PRIM": 8, |
| "I-TYPE": 6, |
| "I-VAR": 2, |
| "O": 0 |
| }, |
| "layer_norm_eps": 1e-05, |
| "length_penalty": 1.0, |
| "max_length": 20, |
| "max_position_embeddings": 1026, |
| "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_past": true, |
| "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": "float32", |
| "torchscript": false, |
| "type_vocab_size": 10, |
| "typical_p": 1.0, |
| "use_bfloat16": false, |
| "use_cache": true, |
| "vocab_size": 51418 |
| }, |
| "encoder": { |
| "_name_or_path": "cudaizerV2_aer", |
| "add_cross_attention": false, |
| "architectures": [ |
| "RobertaForTokenClassification" |
| ], |
| "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": 1536, |
| "id2label": { |
| "0": "O", |
| "1": "B-VAR", |
| "2": "I-VAR", |
| "3": "B-FUNC", |
| "4": "I-FUNC", |
| "5": "B-TYPE", |
| "6": "I-TYPE", |
| "7": "B-PRIM", |
| "8": "I-PRIM", |
| "9": "B-NUM", |
| "10": "I-NUM", |
| "11": "B-POIN", |
| "12": "I-POIN", |
| "13": "B-PDEC", |
| "14": "I-PDEC", |
| "15": "B-CONS", |
| "16": "I-CONS" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 4096, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "B-CONS": 15, |
| "B-FUNC": 3, |
| "B-NUM": 9, |
| "B-PDEC": 13, |
| "B-POIN": 11, |
| "B-PRIM": 7, |
| "B-TYPE": 5, |
| "B-VAR": 1, |
| "I-CONS": 16, |
| "I-FUNC": 4, |
| "I-NUM": 10, |
| "I-PDEC": 14, |
| "I-POIN": 12, |
| "I-PRIM": 8, |
| "I-TYPE": 6, |
| "I-VAR": 2, |
| "O": 0 |
| }, |
| "layer_norm_eps": 1e-05, |
| "length_penalty": 1.0, |
| "max_length": 20, |
| "max_position_embeddings": 1026, |
| "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_past": true, |
| "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": "float32", |
| "torchscript": false, |
| "type_vocab_size": 10, |
| "typical_p": 1.0, |
| "use_bfloat16": false, |
| "use_cache": true, |
| "vocab_size": 51418 |
| }, |
| "eos_token_id": 2, |
| "is_encoder_decoder": true, |
| "model_type": "encoder-decoder", |
| "pad_token_id": 1, |
| "torch_dtype": "float32", |
| "transformers_version": "4.40.1" |
| } |
|
|
