|
T5 fp16 issue is fixed
|
|
9
|
932
|
July 24, 2021
|
|
RobertaClassificationHead - reduce dense layer dimension?
|
|
0
|
23
|
July 23, 2021
|
|
MT5 Decoding in wrong language
|
|
0
|
18
|
July 23, 2021
|
|
Multiple choice with variable number of choices
|
|
0
|
22
|
July 23, 2021
|
|
Tokenizer taking lot of memory
|
|
1
|
24
|
July 22, 2021
|
|
Transformers notebooks / summary of the tasks
|
|
0
|
18
|
July 22, 2021
|
|
How to measure accuracy while fine-tuning bert-base model?
|
|
1
|
57
|
July 22, 2021
|
|
DeepSpeed with GPT2-XL on Colab
|
|
1
|
254
|
July 22, 2021
|
|
Train GPT2 from scratch (Tensorflow) - Loss function
|
|
1
|
282
|
July 21, 2021
|
|
Hidden states embedding tensors
|
|
4
|
93
|
July 21, 2021
|
|
Masked language modelling with specific entities or POS
|
|
0
|
24
|
July 21, 2021
|
|
Fine-tuning XLNet for permutation language modeling: what is the required format of the train data?
|
|
0
|
18
|
July 21, 2021
|
|
Profanity algorithm
|
|
0
|
15
|
July 21, 2021
|
|
ValueError: `mask_length` has to be smaller than `sequence_length`, while finetuning Wav2vec2.0
|
|
3
|
36
|
July 21, 2021
|
|
A potential in-place operation that caused an RuntimeError
|
|
2
|
238
|
July 20, 2021
|
|
Value error : Connection error
|
|
6
|
1281
|
July 20, 2021
|
|
Differences between Config.from_pretrained and Model.from_pretrained
|
|
1
|
27
|
July 20, 2021
|
|
Continual pre-training vs. Fine-tuning a language model with MLM
|
|
0
|
24
|
July 20, 2021
|
|
Adjusting parameters for the FC layers at the end
|
|
1
|
47
|
July 20, 2021
|
|
Get output embeddings out of a transformer model
|
|
4
|
381
|
July 20, 2021
|
|
Multiple training will give exactly the same result except for the first time
|
|
1
|
27
|
July 19, 2021
|
|
AutoModel never runs with multiprocessing
|
|
0
|
25
|
July 19, 2021
|
|
Distilbert Seq2clas
|
|
4
|
31
|
July 19, 2021
|
|
How to finetune mT5
|
|
0
|
31
|
July 19, 2021
|
|
What is the `tie_word_embeddings` option exactly doing?
|
|
1
|
50
|
July 19, 2021
|
|
Minor Bug: HF (run_text_classification) attempts to use XLA on CUDA device
|
|
3
|
28
|
July 19, 2021
|
|
Save only best model in Trainer
|
|
4
|
42
|
July 19, 2021
|
|
`run_glue.py` with my own dataset of one-sentence input
|
|
6
|
623
|
July 18, 2021
|
|
Multiple Mask Tokens
|
|
3
|
1275
|
July 18, 2021
|
|
How is the "Auto Model For Sequence Classification" architecture?
|
|
2
|
33
|
July 18, 2021
|
