|
What is the difference between T5 and BART model?
|
|
0
|
13
|
December 2, 2021
|
|
Bigger batch size, the lower throughput and GPU usage？
|
|
0
|
10
|
December 2, 2021
|
|
Logging training accuracy using Trainer class
|
|
8
|
1378
|
December 2, 2021
|
|
With DataCollator, there is still "KeyError: 'loss'"
|
|
0
|
16
|
December 2, 2021
|
|
Is Int8 quantization training possible while using deepspeed?
|
|
0
|
17
|
December 1, 2021
|
|
Know more about the use of Hugging Face's transformers library
|
|
0
|
23
|
December 1, 2021
|
|
NER pipeline aggregation for BILOU
|
|
0
|
25
|
December 1, 2021
|
|
How to use inputs_embeds in generate()?
|
|
3
|
521
|
December 1, 2021
|
|
Optimising performance non-standard systems
|
|
1
|
171
|
November 30, 2021
|
|
[HELP] Model Evaluation for NER yields different results (sklearn vs metric.compute())
|
|
3
|
191
|
November 30, 2021
|
|
Transfer learning
|
|
3
|
112
|
November 30, 2021
|
|
RuntimeError when running on Colab GPU
|
|
2
|
113
|
November 28, 2021
|
|
Continual pre-training vs. Fine-tuning a language model with MLM
|
|
5
|
205
|
November 30, 2021
|
|
How to preserve Html when processing(paraphrasing)
|
|
3
|
111
|
November 21, 2021
|
|
Summarization on long documents
|
|
49
|
8647
|
November 27, 2021
|
|
Using Seq2SeqTrainer to eval during training?
|
|
1
|
106
|
November 27, 2021
|
|
EncoderDecoderModel generate text for a ViT as encoder
|
|
0
|
60
|
November 27, 2021
|
|
BERT vs GPT architectural, conceptual and implemetational differences
|
|
0
|
64
|
November 26, 2021
|
|
Need help training Speech2Text from scratch
|
|
0
|
56
|
November 26, 2021
|
|
How to get the predicted labels per epoch or step for the huggingface.transformers Trainer?
|
|
1
|
113
|
November 26, 2021
|
|
Shared cache-dir licensing
|
|
0
|
83
|
November 26, 2021
|
|
Big `generate()` refactor
|
|
7
|
984
|
November 26, 2021
|
|
Beam search (FlaxT5) generates PAD tokens mid generation
|
|
1
|
84
|
November 25, 2021
|
|
How to generate a sequence using inputs_embeds instead of input_ids?
|
|
3
|
297
|
November 25, 2021
|
|
Generate multiple summaries
|
|
0
|
72
|
November 25, 2021
|
|
Can trainer.predict() return multiple generations for each sample?
|
|
1
|
113
|
November 25, 2021
|
|
Replace weights in TFBertModel
|
|
0
|
93
|
November 25, 2021
|
|
How to customize output layer (activate function) of existing models with training arguments?
|
|
0
|
61
|
November 25, 2021
|
|
Trainer CUDA OOM error when saving optimizer
|
|
0
|
68
|
November 25, 2021
|
|
Deepspeed ZeRO Inference
|
|
1
|
92
|
November 24, 2021
|
