Skip to content

Issues: locuslab/tofu

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

16 Open 23 Closed
16 Open 23 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

Upload Llama Unlearning Checkpoints
#46 opened Dec 5, 2024 by shariqahn
Unusual Model Utility Gap: Gradient Difference vs Ascent (Llama2)
#45 opened Dec 2, 2024 by jeongjin0
Is the dpo loss wrong?
#44 opened Nov 25, 2024 by HaomingX
Which dataset should we use for evaluate?
#43 opened Sep 19, 2024 by Yuda-Jin
1
RuntimeError: 'weight' must be 2-D During Fine-Tuning with Single GPU
#42 opened Sep 12, 2024 by ouerwt
DeepSpeed Zero-3 is not compatible with low_cpu_mem_usage=True or with passing a device_map
#38 opened Aug 6, 2024 by zhmzm
Inquiry about Constructing Datasets with Elaborate Prompt
#33 opened May 15, 2024 by tbozhong
The implementation of Truth Ratio and Probability is different from the definition in the paper
#26 opened Apr 3, 2024 by wzunknown
13
question about retain_perturbed.json in datasets locuslab/TOFU
#24 opened Apr 2, 2024 by wtma1999
1
The huggingface leaderboard page is showing Runtime Error
#22 opened Apr 1, 2024 by wzunknown
One of the inputs missing for DPO loss
#20 opened Mar 28, 2024 by chrisliu298
4
Getting truth ratio always 1
#19 opened Mar 25, 2024 by shaswati1
13
Dataset contents issues
#18 opened Mar 25, 2024 by molereddy
4
eval generates answer same as dataset
#16 opened Mar 19, 2024 by shaswati1
9
Issues introduced by refactoring and other miscellaneous
#14 opened Mar 16, 2024 by molereddy
9
Unable to train fintuned LoRA on forget
#10 opened Mar 7, 2024 by shaswati1
@pratyushmaini
ProTip! Mix and match filters to narrow down what you’re looking for.