🤗Transformers

Topic	Replies	Views	Activity
AttributeError: 'TrainOutput' object has no attribute 'metrics' when finetune custom dataset 🤗Transformers	3	2522	January 4, 2021
Easy way to implement annealing temperature softmax 🤗Transformers	1	1236	January 4, 2021
Api and parameters change from transofrmers 2.5.1 to 3.5.1 for GPT2 🤗Transformers	0	240	January 4, 2021
Model saving results in a small size checkpoint 🤗Transformers	1	634	January 4, 2021
Is there a way to return the "decoder_input_ids" from "tokenizer.prepare_seq2seq_batch"? 🤗Transformers	5	3358	December 29, 2020
RoBERTa Tokenizer supported characters 🤗Transformers	0	631	December 24, 2020
Sampling with FSMTForConditionalGeneration 🤗Transformers	1	328	December 24, 2020
Recommend argument values for transformers.generation_utils.GenerationMixin.generate() for summarization and translation tasks? 🤗Transformers	1	384	December 24, 2020
Why loss printed by fit() differs from loss using custom loop for huggingface RoBERTa? 🤗Transformers	0	323	December 23, 2020
Batch inference using tfserving/kfserving 🤗Transformers	0	523	December 22, 2020
About the origin of the model category names in `AutoModelWithLMHead` 🤗Transformers	2	1542	December 21, 2020
Unable to import Hugging Face transformers 🤗Transformers	2	2069	December 21, 2020
Huggingface Transformer code successfully gets executed on amazon web services but not on other server 🤗Transformers	1	1366	December 20, 2020
Transformers Tokenizer on GPU? 🤗Transformers	3	15340	December 17, 2020
Streamlit app with PyTorch/HuggingFace Transformers crashes when deployed to Heroku 🤗Transformers	0	863	December 16, 2020
Loading Lower Layers of Model 🤗Transformers	1	2180	December 16, 2020
Fine tune a saved model with custom tokenizer 🤗Transformers	3	2982	December 15, 2020
Dropout before layer normalization 🤗Transformers	0	1015	December 15, 2020
BertForSequenceClassification finetune training loss and accuracy have some problem 🤗Transformers	0	873	December 14, 2020
Dynamic attention mask during GPT-2 training 🤗Transformers	0	851	December 11, 2020
XLNet ONNX Model giving error: "Attempting to broadcast an axis by a dimension other than 1" 🤗Transformers	0	1898	December 10, 2020
Diverse Generations for pseudolabeling 🤗Transformers	7	1702	December 10, 2020
Tips for PreTraining BERT from scratch 🤗Transformers	19	9868	December 10, 2020
Recover the attention weights matrix with Reformer model 🤗Transformers	1	311	December 9, 2020
Fine-tuning seq2seq: Helsinki-NLP 🤗Transformers	4	2283	December 8, 2020
Cross-validation for BERT models 🤗Transformers	0	989	December 8, 2020
Training TransfoXL/GPT2 with fastai gives error 🤗Transformers	2	337	December 8, 2020
Length_penalty not influencing results (Bart, Pegasus) 🤗Transformers	1	831	December 8, 2020
Advice to speed and performance 🤗Transformers	4	7238	December 7, 2020
Gradients of BERT layer outputs to inputs 🤗Transformers	0	1590	December 7, 2020