|
Stable Diffusion NSFW flag
|
|
2
|
6274
|
September 7, 2022
|
|
`FlaxBertModel.from_pretrained("bert-base-cased")` has weights missing?
|
|
0
|
289
|
September 5, 2022
|
|
Any way to normalize a pipeline output?
|
|
0
|
251
|
September 5, 2022
|
|
HuggingFace Trainer() does nothing - only on Vertex AI workbench, works on colab
|
|
2
|
1847
|
September 5, 2022
|
|
Distributed Finetuning with Trainer
|
|
0
|
498
|
September 4, 2022
|
|
Are there any higher version transformers compatible with transformers==3.0.2
|
|
0
|
207
|
September 4, 2022
|
|
How does prepare inputs for generation work in GPT-2?
|
|
0
|
918
|
September 2, 2022
|
|
Building an Efficient NLP API
|
|
0
|
236
|
September 2, 2022
|
|
Question about greedy_search
|
|
4
|
1811
|
June 18, 2021
|
|
Changing resolution of transformer models for training
|
|
0
|
638
|
September 2, 2022
|
|
Is it possible to tokenize multiple text modalities?
|
|
1
|
451
|
September 1, 2022
|
|
How to constrain mBart decoding to generate English-only output?
|
|
0
|
418
|
August 31, 2022
|
|
Transformer model parallel does not work with Pytorch DDP for multi-node training
|
|
0
|
515
|
September 1, 2022
|
|
Getting probability distributions of T5 outputs
|
|
0
|
1148
|
August 30, 2022
|
|
Early Stopping using PPL for a XLMRobertaForMaskedLM model
|
|
3
|
720
|
August 29, 2022
|
|
Very long warning when running rag-end2end-retriever
|
|
1
|
1038
|
August 26, 2022
|
|
Can `Trainer` be customised for curriculum learning?
|
|
0
|
902
|
August 26, 2022
|
|
I get different answer using Hosted inference API and pipeline object
|
|
0
|
289
|
August 26, 2022
|
|
Speeding up T5 inference :rocket:
|
|
17
|
13060
|
August 26, 2022
|
|
The training loss(logging steps) will drop suddenly after each epoch? Help me plz! Orz
|
|
1
|
1159
|
August 26, 2022
|
|
@shamanez What is the recommended KB size to fine tune the context encoder of the RAG
|
|
1
|
243
|
August 26, 2022
|
|
Adding a documentation to save the best checkpoint during the training in summarization example project
|
|
0
|
172
|
August 26, 2022
|
|
Text generation using custom constraints
|
|
0
|
682
|
August 25, 2022
|
|
Trainer and TrainingArguments - gradual unfreezing
|
|
2
|
646
|
August 25, 2022
|
|
How is the encoding done for transformers? What encoder is used?
|
|
4
|
545
|
August 25, 2022
|
|
Fine-tuning with load_in_8bit and inference without load_in_8bit possible?
|
|
4
|
24129
|
August 23, 2022
|
|
Is wandb in Trainer configured for distributed training?
|
|
3
|
1961
|
August 23, 2022
|
|
Transformers, limiting output to 200 words
|
|
0
|
290
|
August 23, 2022
|
|
Wav2Vec2ProcessorWithLM intended usage
|
|
0
|
992
|
August 23, 2022
|
|
Evaluation error: CUDA out of memory
|
|
0
|
722
|
August 22, 2022
|