StackOverflow Questions for Tag: huggingface-transformers

user2543622

Reputation: 6796

Using sentence transformers with limited access to internet

pythonnlphuggingface-transformerssentence-transformers

Score: 1

Answers: 2

Andrey

Reputation: 6377

Ollama model quality is worse than similar huggingface model

huggingface-transformersollama

Score: 0

Answers: 0

Varshini Ranganath

Reputation: 1

How to detrain a Mistral-based Llama model?

huggingface-transformersllamafine-tuningmistral-7b

Score: -1

Answers: 0

bbh

Reputation: 1

How to modify the Hugging Face transformers library to ensure all internal calls point to the files under a custom directory?

pythonhuggingface-transformers

Score: 0

Answers: 0

Jose Ramon

Reputation: 5386

Load Phi 3 model extract attention layer and visualize it

pythonpytorchhuggingface-transformersattention-model

Score: 3

Answers: 1

mitra mirshafiee

Reputation: 503

Where is the HuggingFace model saved in when loading a model on colab?

nlphuggingface-transformershuggingface

Score: 1

Answers: 1

Arthur

Reputation: 2400

How can I load a pretrained transformers model that was manually downloaded?

pythonhuggingface-transformers

Score: 1

Answers: 2

Solitary-Coder

Reputation: 1

Runtime Error while trying to train RTDetrV2 with Transformer

pythonmachine-learningpytorchhuggingface-transformersroboflow

Score: 0

Answers: 0

Aaditya Ura

Reputation: 12679

KeyError: 'eval_loss' in Hugginface Trainer

python-3.xmachine-learningpytorchhuggingface-transformershuggingface-tokenizers

Score: 3

Answers: 3

Preetham

Reputation: 1

How to Align the Ground Truth Labels and the Student Logits Labels in Knowledge Distillation?

nlphuggingface-transformerslarge-language-modelcross-entropylogits

Score: -1

Answers: 0

Minh Ngo

Reputation: 79

HuggingFace - model.generate() is extremely slow when I load from checkpoint

pythonpytorchhuggingface-transformers

Score: 7

Answers: 1

Hariharan

Reputation: 1

How can I configure OpenVINO to automatically use GPU, CPU, or NPU for model inference?

deep-learningintelhuggingface-transformersopenvinoaiml

Score: 0

Answers: 1

mad

Reputation: 11

Issue with Loading BLIP Processor and Model for Image Captioning

tensorflowpytorchhuggingface-transformershuggingface

Score: 0

Answers: 0

Arij Aladel

Reputation: 555

T5Tokenizer requires the SentencePiece library but it was not found in your environment

huggingface-transformersgoogle-colaboratory

Score: 12

Answers: 6

Sebastian-CV-ML

Reputation: 11

NLP: LayoutXLM (HF model) inference- index out of bounds: 0 <= tmp30 < 1L

stringnlphuggingface-transformerslarge-language-modelhuggingface-tokenizers

Score: 0

Answers: 0

landings

Reputation: 770

Fine-tuning a Pretrained Model with Quantization and AMP: Scaler Error "Attempting to Unscale FP16 Gradients"

pythonpytorchnlphuggingface-transformersfine-tuning

Score: 1

Answers: 1

Nick

Reputation: 165

transformers No module named 'keras.engine'

pythonkerashuggingface-transformers

Score: 2

Answers: 1

Akshit Gulyan

Reputation: 71

Why does HuggingFace-provided Deepseek code result in an 'Unknown quantization type' error?

pythonmachine-learninghuggingface-transformershuggingface

Score: 6

Answers: 2

Charlie Parker

Reputation: 5199

How does one set the pad token correctly (not to eos) during fine-tuning to avoid model not predicting EOS?

machine-learningpytorchhuggingface-transformershuggingfacehuggingface-tokenizers

Score: 11

Answers: 7

Aman Kumar Happy

Reputation: 1

Fixing Hugging Face Login Issue (504 Gateway Timeout & Invalid Token Error)

pythonerror-handlinghuggingface-transformershuggingface-tokenizers

Score: -6

Answers: 1

PreviousPage 1Next

StackOverflow Questions for Tag: huggingface-transformers

Using sentence transformers with limited access to internet

Ollama model quality is worse than similar huggingface model

How to detrain a Mistral-based Llama model?

How to modify the Hugging Face transformers library to ensure all internal calls point to the files under a custom directory?

Load Phi 3 model extract attention layer and visualize it

Where is the HuggingFace model saved in when loading a model on colab?

How can I load a pretrained transformers model that was manually downloaded?

Runtime Error while trying to train RTDetrV2 with Transformer

KeyError: &#39;eval_loss&#39; in Hugginface Trainer

How to Align the Ground Truth Labels and the Student Logits Labels in Knowledge Distillation?

HuggingFace - model.generate() is extremely slow when I load from checkpoint

How can I configure OpenVINO to automatically use GPU, CPU, or NPU for model inference?

Issue with Loading BLIP Processor and Model for Image Captioning

T5Tokenizer requires the SentencePiece library but it was not found in your environment

NLP: LayoutXLM (HF model) inference- index out of bounds: 0 &lt;= tmp30 &lt; 1L

Fine-tuning a Pretrained Model with Quantization and AMP: Scaler Error &quot;Attempting to Unscale FP16 Gradients&quot;

transformers No module named &#39;keras.engine&#39;

Why does HuggingFace-provided Deepseek code result in an &#39;Unknown quantization type&#39; error?

How does one set the pad token correctly (not to eos) during fine-tuning to avoid model not predicting EOS?

Fixing Hugging Face Login Issue (504 Gateway Timeout &amp; Invalid Token Error)

KeyError: 'eval_loss' in Hugginface Trainer

NLP: LayoutXLM (HF model) inference- index out of bounds: 0 <= tmp30 < 1L

Fine-tuning a Pretrained Model with Quantization and AMP: Scaler Error "Attempting to Unscale FP16 Gradients"

transformers No module named 'keras.engine'

Why does HuggingFace-provided Deepseek code result in an 'Unknown quantization type' error?

Fixing Hugging Face Login Issue (504 Gateway Timeout & Invalid Token Error)