Logo Questions Linux Laravel Mysql Ubuntu Git Menu
 

New posts in huggingface-transformers

Speeding up load time of LLMs

Loading a HuggingFace model on multiple GPUs using model parallelism for inference

AttributeError: 'tensorflow.python.framework.ops.EagerTensor' object has no attribute 'to_tensor'

huggingface longformer memory issues

ImportError: Using `low_cpu_mem_usage=True` or a `device_map` requires Accelerate: `pip install accelerate`

How can i get all outputs of the last transformer encoder in bert pretrained model and not just the cls token output?

Why does llama-index still require an OpenAI key when using Hugging Face local embedding model?

Restrict Vocab for BERT Encoder-Decoder Text Generation

Converting a dataset to CoNLL format. Label remaining tokens with O

Transformers gets killed for no reason on linux

RuntimeError: Failed to import transformers.pipelines because of the following error (look up to see its traceback): initialization failed

Semantic searching using Google flan-t5

Can mT5 model on Huggingface be used for machine translation?

Saving BERT Sentence Embedding

Loading saved NER back into HuggingFace pipeline?

Is the default `Trainer` class in HuggingFace transformers using PyTorch or TensorFlow under the hood?

Hugging Face Transformers trainer: per_device_train_batch_size vs auto_find_batch_size