Logo Questions Linux Laravel Mysql Ubuntu Git Menu
 

New posts in huggingface-transformers

How do I train a encoder-decoder model for a translation task using hugging face transformers?

why take the first hidden state for sequence classification (DistilBertForSequenceClassification) by HuggingFace

Transformer: Error importing packages. "ImportError: cannot import name 'SAVE_STATE_WARNING' from 'torch.optim.lr_scheduler'"

Use of attention_mask during the forward pass in lm finetuning

HuggingFace BERT `inputs_embeds` giving unexpected result

Understanding BERT vocab [unusedxxx] tokens:

PyTorch torch.no_grad() versus requires_grad=False

How to make a Trainer pad inputs in a batch with huggingface-transformers?

Named Entity Recognition with Huggingface transformers, mapping back to complete entities

How to encode multiple sentences using transformers.BertTokenizer?

Difficulty in understanding the tokenizer used in Roberta model

Add dense layer on top of Huggingface BERT model

How does torch.distributed.barrier() work

Updating a BERT model through Huggingface transformers

Training TFBertForSequenceClassification with custom X and Y data

Get probability of multi-token word in MASK position

Tokens to Words mapping in the tokenizer decode step huggingface?

How to get immediate next word probability using GPT2 model?

How to load the saved tokenizer from pretrained model