|
Outputting relevance scores
|
|
0
|
541
|
September 25, 2020
|
|
Text generation, text2text: change output vocabulary, output distribution dimensions
|
|
0
|
538
|
March 11, 2021
|
|
How to frozen the attention map in BERT
|
|
0
|
536
|
October 6, 2021
|
|
Error making predictions using LMM (LLaVA) model on multiple GPUs
|
|
0
|
536
|
March 27, 2024
|
|
Making a dataset that read the labels from parent folders
|
|
0
|
535
|
December 2, 2021
|
|
ASR on inference endpoints
|
|
1
|
378
|
February 11, 2024
|
|
How do I create a commercially usable workflow that can accurately swap faces on ComfyUI?
|
|
0
|
95
|
March 3, 2025
|
|
How big are differences between transformer implementations
|
|
0
|
532
|
April 26, 2022
|
|
Extending the tokenizer affects model generation
|
|
3
|
149
|
December 19, 2024
|
|
Pretrain encoder of tf T5 model
|
|
0
|
529
|
October 19, 2020
|
|
Modify HF model for training
|
|
1
|
374
|
December 22, 2023
|
|
Docker image "THIS IMAGE IS DEPRECATED and is scheduled for DELETION." message
|
|
0
|
94
|
January 6, 2025
|
|
mBART embedding matrix prunning
|
|
0
|
527
|
May 11, 2021
|
|
Downloading larger models with xet fails on macOS
|
|
3
|
149
|
June 5, 2025
|
|
Error while Fine tuning Zero shot classification model fb-bart-large-mnli
|
|
0
|
521
|
June 6, 2023
|
|
BART: get activation maps for encoder and decoder
|
|
0
|
521
|
November 3, 2021
|
|
How can I implement active learning in BERT?
|
|
0
|
520
|
November 9, 2021
|
|
Huggingface using only half of the cores for inference
|
|
0
|
517
|
September 6, 2023
|
|
NER - Lab Reports, Vitals
|
|
0
|
517
|
March 1, 2022
|
|
How to Implement Numerical Inference in a Text Generation Problem
|
|
0
|
516
|
May 17, 2022
|
|
Text to text classification
|
|
0
|
515
|
March 12, 2022
|
|
Best multi-GPU setup for finetuning and inference?
|
|
0
|
513
|
July 3, 2024
|
|
Windows 11 does not see my 2nd GPU (4090 + 4080)
|
|
2
|
296
|
October 3, 2024
|
|
MRPC Reproducibility with transformers-4.1.0
|
|
1
|
362
|
December 20, 2020
|
|
Possible error in Dataset elasticsearch
|
|
0
|
508
|
May 20, 2022
|
|
AOTInductor with Llama-3.2-3B-Instruct
|
|
0
|
90
|
November 14, 2024
|
|
Hugging Face and Distributed Training: DDP/DP Implementation Help Needed
|
|
0
|
506
|
February 14, 2024
|
|
Treating Punctuatio restoration as Seq2Seq task
|
|
0
|
506
|
December 11, 2020
|
|
[Transformer] how to tokenize nested object dataset?
|
|
0
|
498
|
November 23, 2022
|
|
How to use huge target data without source data
|
|
0
|
497
|
May 2, 2022
|
|
ValueError: expected sequence of length 128 at dim 1 (got 68)
|
|
0
|
496
|
October 25, 2023
|
|
Fine tuning for summarization script error
|
|
0
|
495
|
August 24, 2022
|
|
Additional pre-training objective function
|
|
0
|
495
|
July 3, 2021
|
|
What can you fine tune with 2x A6000s?
|
|
1
|
350
|
December 5, 2023
|
|
Does higher work with huggingface (hugging face, HF) models? e.g. ViT?
|
|
1
|
350
|
March 19, 2023
|
|
Input batch size not matching Target batch size
|
|
0
|
88
|
October 26, 2024
|
|
Peft following bits and bytes seems to have no effect on LLM
|
|
0
|
493
|
January 31, 2024
|
|
Looking for a simple tutorial on how to fine tune a model for relation extraction
|
|
0
|
493
|
July 2, 2022
|
|
Seq2SeqTrainingArguments due to missing accelerate library which is actually installed
|
|
3
|
246
|
March 17, 2024
|
|
LogitsProcessor guide
|
|
0
|
491
|
July 18, 2022
|
|
Roberta For Urdu Text Classification
|
|
0
|
489
|
December 23, 2021
|
|
How to compute metrics when ground truth and predictions have different data?
|
|
0
|
487
|
January 4, 2023
|
|
Unavailable wav2vec2 tokenizer
|
|
0
|
487
|
December 10, 2021
|
|
Not able to predict using Transformers Trainer class
|
|
2
|
158
|
October 2, 2024
|
|
Multi GPU traning with Accelerator vs Trainer
|
|
2
|
158
|
August 6, 2024
|
|
SportsBot Training Data and Modal
|
|
1
|
344
|
May 30, 2023
|
|
Need advise for fine-tuning BERT on opinion mining
|
|
0
|
486
|
October 25, 2021
|
|
How to ensure my custom Trainer is using my custom TrainerState and TrainerControl?
|
|
1
|
343
|
June 14, 2024
|
|
Tokenizer for Translation Pipeline with Bert2Bert EncoderDecoder
|
|
0
|
484
|
February 23, 2022
|
|
Fine-tune MT5ConditionalGeneration for question generation
|
|
0
|
483
|
January 4, 2022
|