Logo Questions Linux Laravel Mysql Ubuntu Git Menu
 

New posts in huggingface-transformers

Trainer huggingface - RuntimeError: cannot pin 'torch.cuda.FloatTensor' only dense CPU tensors can be pinned

How are the weights of the Mistral models reinitialized in Huggingface?

How to split input text into equal size of tokens, not character length, and then concatenate the summarization results for Hugging Face transformers

Using huggingface fill-mask pipeline to get more than 5 suggestions

Huggingface GPT2 loss understanding

ValueError: Tokenizer class LlamaTokenizer does not exist or is not currently imported

Running huggingface Bert tokenizer on GPU

Using huggingface library gives an error: KeyError: 'logits'

Why we need the init_weight function in BERT pretrained model in Huggingface Transformers?

ImportError: Using the Trainer with PyTorch requires accelerate = 0.20.1

BERT get sentence embedding

How to fix "Trainer: evaluation requires an eval_dataset" in Huggingface Transformers?

Mistral model generates the same embeddings for different input texts

How to save the LLM2Vec model as a HuggingFace PreTrainedModel object?