Hugging Face Forums

Topic	Replies	Views	Activity
No PreTrainedTokenizerFast for Deberta-V3, no doc_stride 🤗Tokenizers	0	924	July 13, 2022
Vectorization of a DNA sequence 🤗Datasets	1	574	July 13, 2022
Creating summaries of fixed length with PEGASUS model 🤗Transformers	1	474	July 13, 2022
Set_transform vs with_transform Beginners	1	4864	July 13, 2022
Use external embeddings 🤗Transformers	0	372	July 13, 2022
How to train a custom EncoderDecoderModel with KLD loss Beginners	0	425	July 13, 2022
How to load model saved in local (Visual Transformer ViT)? 🤗Transformers	1	1609	July 13, 2022
Multilingual NER Extraction Models	1	540	July 13, 2022
KeyError: 'loss' when fine-tuning a Transformer model Beginners	7	2464	July 12, 2022
Using Batch Encodings 🤗Transformers	0	695	July 12, 2022
Infilling multiple mask spans with BartForConditionalGeneration Intermediate	0	410	July 12, 2022
How to mask multiple tokens in BartForConditionalGeneration? Beginners	3	1092	July 12, 2022
Outputting gradients with respect to Attentions from a trained model? Beginners	0	284	July 12, 2022
Reason for discrepancy between loss calculation in XLNetLMHeadModel and GPT2LMHeadModel 🤗Transformers	0	429	July 12, 2022
Very low GPU usage when translating text, datasets not helping 🤗Transformers	3	5834	July 12, 2022
PyTorch version Beginners	7	1682	July 12, 2022
How to use the question-answering pipeline in batch mode? Beginners	0	405	July 12, 2022
Seq2Seq model for distilgpt2 Beginners	0	861	July 12, 2022
Different lm_head size and vocab_size 🤗Transformers	0	857	July 12, 2022
Troubleshooting help? Everything just hangs 🤗Accelerate	2	3360	July 12, 2022
Reduce inference latency of text embedding endpoint Amazon SageMaker	1	1109	July 12, 2022
How to train on those datasets that have multi-characters Beginners	0	210	July 12, 2022
Rewriting generate function for manual decoder input 🤗Transformers	7	3558	July 11, 2022
Huggingface Vision Dataset - the right way to use it? 🤗Datasets	5	1280	July 11, 2022
RuntimeError - invalid multinomial distribution (with replacement=False, not enough non-negative category to sample) 🤗Transformers	0	392	July 11, 2022
Tokenizer from own vocab 🤗Tokenizers	0	457	July 11, 2022
Concurrent Users Spaces	2	1293	July 11, 2022
Which tokenizer does "rouge" metric uses under the hood? 🤗Datasets	2	2198	July 11, 2022
Mutli GPU freezes on Roberta Pretraining Beginners	6	2064	July 11, 2022
Apply multiple rows of pandas dataframe to text2text-generation pipeline 🤗Transformers	0	572	July 11, 2022