Skip to content

Issues: lxe/simple-llm-finetuner

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Clear current search query, filters, and sorts
34 Open 15 Closed
34 Open 15 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Is CUDA 12.0 supported? question Further information is requested
#8 opened Mar 22, 2023 by vadi2 updated Mar 22, 2023
1
Collecting info on memory requirements question Further information is requested
#2 opened Mar 22, 2023 by jmiskovic updated Mar 22, 2023
1
Inference output text keeps running on... bug Something isn't working question Further information is requested
#1 opened Mar 22, 2023 by lxe updated Mar 23, 2023
1
Finetuning in unsupported language question Further information is requested
#15 opened Mar 23, 2023 by jumasheff updated Mar 25, 2023
2
Can Nivdia 3090 with 24G video memory support finetune? question Further information is requested
#7 opened Mar 22, 2023 by pczzy updated Mar 26, 2023
4
Examples to get started with enhancement New feature or request
#11 opened Mar 22, 2023 by vadi2 updated Mar 27, 2023
4
Traceback during inference. bug Something isn't working
#6 opened Mar 22, 2023 by Hello1024 updated Mar 28, 2023
8
Error during Training RuntimeError: mat1 and mat2 shapes cannot be multiplied (511x2 and 3x4096) bug Something isn't working
#25 opened Mar 26, 2023 by kasakh updated Mar 28, 2023
2
Not a problem - but like people should know documentation Improvements or additions to documentation
#26 opened Mar 26, 2023 by Atlas3DSS updated Mar 28, 2023
2
Attempting to use 13B in the simple tuner - bug Something isn't working
#28 opened Mar 27, 2023 by Atlas3DSS updated Mar 30, 2023
2
how to finetune with 'system information'
#30 opened Mar 30, 2023 by mhyeonsoo updated Mar 31, 2023
1
Training using long stories instead of question/response question Further information is requested
#24 opened Mar 26, 2023 by leszekhanusz updated Apr 3, 2023
3
"error" in training - AttributeError: 'CastOutputToFloat' object has no attribute 'weight', RuntimeError: Only Tensors of floating point and complex dtype can require gradients bug Something isn't working
#29 opened Mar 28, 2023 by GreenTeaBD updated Apr 6, 2023
5
AttributeError: type object 'Dataset' has no attribute 'from_list'
#36 opened Apr 5, 2023 by Datta0 updated Apr 7, 2023
3
question: could the model trained be used for alpaca.cpp? question Further information is requested
#20 opened Mar 24, 2023 by goog updated Apr 7, 2023
2
Suggestion to improve UX
#32 opened Apr 2, 2023 by ch3rn0v updated Apr 9, 2023
3
Getting OOM
#46 opened Apr 12, 2023 by alior101 updated Apr 24, 2023
2
Issue in train in colab colab
#42 opened Apr 9, 2023 by fermions75 updated Apr 24, 2023
7
Multi GPU running
#51 opened May 10, 2023 by Shashika007 updated May 10, 2023
LLaMATokenizer vs LlamaTokenizer class names question Further information is requested
#22 opened Mar 25, 2023 by vadi2 updated May 20, 2023
5
In trainer.py, ignore the last token is not suitable for all situations.
#53 opened Jun 17, 2023 by HCTsai updated Jun 17, 2023
[Request] QLoRA support
#55 opened Jun 29, 2023 by CoolOppo updated Jun 29, 2023
[Request] Mac ARM support
#56 opened Jul 2, 2023 by voidcenter updated Jul 2, 2023
M1/M2 Metal support?
#57 opened Jul 22, 2023 by itsPreto updated Jul 22, 2023
RuntimeError: expected scalar type Half but found Float
#52 opened May 24, 2023 by jasperan updated Aug 8, 2023
3
ProTip! no:milestone will show everything without a milestone.