|
Trainer errors out when concatenating different sequence length batches with distributed training and IterableDataset
|
|
0
|
204
|
October 2, 2023
|
|
Image to text model that can take an additional text input
|
|
1
|
282
|
October 2, 2023
|
|
What is the right way of developing my own model based on a pretrained transformer?
|
|
1
|
506
|
October 2, 2023
|
|
Positional encoding error in RoBERTa
|
|
1
|
339
|
October 2, 2023
|
|
Boosting the speed of a translation model Helsinki-NLP/opus-mt-en-ar
|
|
0
|
749
|
October 2, 2023
|
|
Dino2 for classification has wrong number of labels
|
|
2
|
474
|
October 2, 2023
|
|
Finetuning cost estimator formula
|
|
0
|
521
|
October 1, 2023
|
|
How to use run_classification.py to fine tuning bert in imdb?
|
|
0
|
297
|
October 1, 2023
|
|
How to add new language to NLLB tokenizer in Huggingface?
|
|
2
|
1952
|
September 30, 2023
|
|
ValueError: too many values to unpack (expected 2) in text summarization. Possibly due to nested lists?
|
|
1
|
1759
|
September 29, 2023
|
|
Trainer.train() seems to finish almost instantly
|
|
0
|
521
|
September 29, 2023
|
|
Flan T5 fine tuning error
|
|
0
|
524
|
September 29, 2023
|
|
Finetune Llama with PPOTrainer
|
|
2
|
898
|
September 29, 2023
|
|
How to pass `min_length` parameter in generate?
|
|
1
|
342
|
September 29, 2023
|
|
Understanding the docoder attention weights in the Fusion-in-Decoder method
|
|
0
|
375
|
September 29, 2023
|
|
Q&A evaluation: Mismatch in the number of predictions (775) and references (835)
|
|
4
|
3267
|
September 28, 2023
|
|
Is there way to convert the Donut model to openvino format
|
|
0
|
172
|
September 28, 2023
|
|
Batched generation_config/kwargs for the `transformers.generation.utils.generate` function
|
|
0
|
193
|
September 28, 2023
|
|
Convert torch tensor to String Representation Value
|
|
1
|
3552
|
September 28, 2023
|
|
Use custom model for mask filling using pipeline
|
|
0
|
340
|
September 27, 2023
|
|
Costumizing MASKed tokens
|
|
1
|
243
|
September 27, 2023
|
|
Conversational pipeline by huggingface transformer taking too long to generate output
|
|
0
|
843
|
September 27, 2023
|
|
Vall-e and Vall-e X implementation
|
|
0
|
398
|
September 27, 2023
|
|
Debugging the compute_loss function for custom dice loss in binary segmentation tasks
|
|
0
|
404
|
September 27, 2023
|
|
Avoid installation of pytorch with transformers for onnx inference
|
|
0
|
132
|
September 26, 2023
|
|
How does attention key/value caching work with models that have learned absolute position embeddings?
|
|
0
|
1366
|
September 26, 2023
|
|
Error with DataCollator for SpeechT5
|
|
2
|
389
|
September 26, 2023
|
|
Rouge-L score in Trainer huggingface
|
|
1
|
2045
|
September 25, 2023
|
|
Best transformer model to check grammar
|
|
0
|
325
|
September 24, 2023
|
|
How to turn off text streamer to repeat prompt in the output?
|
|
0
|
328
|
September 23, 2023
|