Pinned issues
Issues
- 3
- 9
Unable to evaluate the model
#9 opened by sglucas - 11
[Reimplementation] Unable to reproduce results -- Training loss curves are similar
#1 opened by maximegmd - 3
Output 0 of ViewBackward0 is a view
#10 opened by clechristophe - 2
how to add it to transformers‘s mdoel??
#11 opened by Dhaizei - 3
No eval_scoring.py file in the repo
#12 opened by cuongtran-uva - 1
quesiton about the noise injection location
#15 opened by zhhao1 - 1
how to add multi-turns function?
#14 opened by Dhaizei - 0
can you suggest about chat tuning?
#13 opened by Dhaizei - 1
- 1
i think "return model" should be within the scope of the NEFTune function, not outside it
#8 opened by Kayce001 - 9
RuntimeError: ``sharded_state_dict`` can only be used when parameters are flatten and sharded.
#2 opened by Sniper970119 - 1
More benchmarks
#6 opened by eyuansu62 - 1
QLoRA implementation
#3 opened by marianbastiUNRN