Issues
- 0
Error: Invalid new-expression of abstract class type torchdistx::detail::{anonymous}::ProxyVariableHooks
#65 opened by Agamya-Yadav - 1
- 1
Problem with __future__ annotation
#59 opened by yash-srivastava19 - 0
- 1
Pretrain Donut model
#58 opened by Wyzix33 - 7
Extending IndicBART or IndicBERT
#57 opened by singhakr - 11
Alternative to installing sentencpiece
#56 opened by Sreyan88 - 1
Evaluation during training BARTforConditionalGeneration pre-training on English corpora
#55 opened by Sreyan88 - 5
Error in BART Monolingual Pre-training.
#54 opened by Ab26 - 0
Support all optimizers and schedulers
#53 opened by prajdabre - 0
Mixtures of denoisers
#52 opened by prajdabre - 0
Add post-norm to the model
#51 opened by prajdabre - 0
Add PEP8 style guide checker workflow
#50 opened by divyanshugit - 0
RuntimeError: The expanded size of the tensor (22) must match the existing size (21) at non-singleton dimension 1. Target sizes: [178, 22, 1] . Tensor sizes: [178, 21, 1]
#49 opened by Ab26 - 12
- 0
Display more information during training
#48 opened by prajdabre - 0
- 0
CPU support
#46 opened by prajdabre - 0
Binary executables for all python scripts
#45 opened by prajdabre - 0
Improve examples
#44 opened by prajdabre - 0
Improve documentation
#43 opened by prajdabre - 0
Adding WandB support
#42 opened by prajdabre - 0
- 7
Some problem with loss
#40 opened by raullese - 6
Error when when trying to pretrain with other language extensions apart from hi
#38 opened by raypretam - 13
some confused of <CUDA out of memory>
#39 opened by raullese - 15
- 21
RuntimeError: [enforce fail at inline_container.cc:145] . PytorchStreamReader failed reading file data/94862161006912: file read failed
#35 opened by raullese - 2
- 1
Some question of pretrain_nmt.py
#33 opened by raullese - 8
- 2
Pretraining Bart on Single corpus
#31 opened by 1029694141 - 3
Using masked inputs at inference time
#20 opened by jaspock - 5
dependency conflicts in requirements.txt
#21 opened by ShivprasadSagare - 1
Broken package in requirements.txt
#23 opened by ShivprasadSagare - 3
Pre-training hangs
#26 opened by jaspock - 7
Unexpected Keyword arguments prompt_params, adaptor_layers, deep_adaptor_tuning, deep_adaptor_tuning_ffn_only, parallel_adaptors
#27 opened by goru001 - 1
- 4
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 64: invalid start byte
#28 opened by oliviersalaun - 12
ImportError: cannot import name 'AutoTokenizer' from 'transformers' (unknown location)
#29 opened by nikhilbyte - 1
GPU Consumption keeps on increasing
#25 opened by nikhilbyte - 4
Trying to pretrain mBART model.
#24 opened by nikhilbyte - 2
- 3
Add xProphetNet model into this toolkit
#19 opened by koukoulala - 2
Train MBART Model: forward() got an unexpected keyword argument 'label_mask'
#18 opened by anhdungitvn - 3
- 3
- 2
- 4
- 2
at train_nmt.py I get RuntimeError: The expanded size of the tensor (30) must match the existing size (25) at non-singleton dimension 1.
#9 opened by GorkaUrbizu