issues
search
neelsjain
/
NEFTune
Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning
MIT License
387
stars
20
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Update README.md
#18
jlhe2000
closed
6 months ago
1
Update README.md
#17
LiChao-cy
opened
11 months ago
0
Update README to announce integration with Ludwig
#16
arnavgarg1
closed
1 year ago
0
quesiton about the noise injection location
#15
zhhao1
closed
1 year ago
1
how to add multi-turns function?
#14
Dhaizei
closed
1 year ago
1
can you suggest about chat tuning？
#13
Dhaizei
closed
1 year ago
0
No eval_scoring.py file in the repo
#12
cuongtran-uva
closed
1 year ago
3
how to add it to transformers‘s mdoel??
#11
Dhaizei
closed
1 year ago
2
Output 0 of ViewBackward0 is a view
#10
clechristophe
closed
1 year ago
3
Unable to evaluate the model
#9
sglucas
closed
11 months ago
9
i think "return model" should be within the scope of the NEFTune function, not outside it
#8
Kayce001
closed
1 year ago
1
Question about output embedding from noised tokens
#7
isamu-isozaki
closed
1 year ago
1
More benchmarks
#6
eyuansu62
closed
1 year ago
1
{RecursionError}maximum recursion depth exceeded while calling a Python object
#5
NormXU
closed
1 year ago
3
Fix typo in utils.py
#4
eltociear
opened
1 year ago
0
QLoRA implementation
#3
ghost
closed
1 year ago
1
RuntimeError: ``sharded_state_dict`` can only be used when parameters are flatten and sharded.
#2
Sniper970119
closed
1 year ago
9
[Reimplementation] Unable to reproduce results -- Training loss curves are similar
#1
maximegmd
closed
11 months ago
11