Skip to content

Issues: TransformerLensOrg/TransformerLens

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

73 Open 151 Closed
73 Open 151 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

[Bug Report] Different results from HuggingFace when using the GPT2 small example complexity-high Very complicated changes for people to address who are quite familiar with the code implementation-inaccuracy Any issues related to our implementation being off from the official version needs-investigation Issues that need to be recreated, or investigated before work can be done
#685 opened Jul 27, 2024 by nreHieW
1 task done
[Question] Why does Transformer Lens only support quantized LLaMA models?
#684 opened Jul 26, 2024 by miguel-kjh
1
[Bug Report] Qwen model implementation is too inaccurate complexity-high Very complicated changes for people to address who are quite familiar with the code implementation-inaccuracy Any issues related to our implementation being off from the official version needs-investigation Issues that need to be recreated, or investigated before work can be done
#683 opened Jul 23, 2024 by bryce13950
1 task done
2
[Proposal] Demo and Tutorial on Patchscopes and "Patching + Generation" complexity-moderate Moderately complicated issues for people who have intermediate experience with the code demo Creating a demo or tutorial
#680 opened Jul 16, 2024 by HenryCai11
1 task done
@HenryCai11
3
[Proposal] Allow tied embeddings complexity-moderate Moderately complicated issues for people who have intermediate experience with the code enhancement New feature or request
#671 opened Jul 12, 2024 by neelnanda-io
1
ValueError: microsoft/Phi-3-mini-128k-instruct not found.
#670 opened Jul 12, 2024 by joykirat18
1
does run_with_cache method support data parallel , how can I do it ?
#669 opened Jul 12, 2024 by Yang-bug-star
[Proposal] Allow recent versions of beartype complexity-simple Simple issues, which may be good for beginners tooling Anything pertaining to outside tools used within the codebase
#665 opened Jul 10, 2024 by jettjaniak
1 task done
6
[Bug Report] Pythia output inconsistent across batch sizes when use_split_qkv_input=True bug Something isn't working complexity-high Very complicated changes for people to address who are quite familiar with the code implementation-inaccuracy Any issues related to our implementation being off from the official version
#661 opened Jul 8, 2024 by oliveradk
1 task done
[Bug Report] RMSNormPre in Transformer_lens is maybe different from Llama source code?
#657 opened Jul 6, 2024 by wangyifei0047
Is it possible to use a locally downloaded model without accessing HF?
#655 opened Jul 4, 2024 by ccp123456
3
[Proposal] Documentation: Map the Act Names to the Transformer complexity-moderate Moderately complicated issues for people who have intermediate experience with the code documentation Improvements or additions to documentation
#644 opened Jun 21, 2024 by JuVogt
1 task done
2
[Proposal] Remove the overhead caused by full_hook.__name__ = (hook.__repr__())?
#631 opened Jun 8, 2024 by verlocks
1
1
[Proposal] Add support for Baichuan1 and Baichuan2 complexity-moderate Moderately complicated issues for people who have intermediate experience with the code
#622 opened Jun 3, 2024 by StarrySeas1
@StarrySeas1
3
[Bug Report] The output from HookedTransformer is not identical compared to Huggingface model for Lllama 3 bug Something isn't working complexity-high Very complicated changes for people to address who are quite familiar with the code
#615 opened May 28, 2024 by iamsimha
1 task done
7
[Proposal] Merge utils and utilities complexity-moderate Moderately complicated issues for people who have intermediate experience with the code refactor Changing something with the code that will either affect external user, or contributors
#612 opened May 27, 2024 by bryce13950
1 task done
@starship006
1
[Feature Request] Add Stopping Criteria support complexity-high Very complicated changes for people to address who are quite familiar with the code enhancement New feature or request
#595 opened May 15, 2024 by Butanium
1
Setup for fine tuned Mistral model ? question Further information is requested
#592 opened May 14, 2024 by SiddhantOjha17
8
[Bug Report] TransformerLens's use of einsum leads to different training dynamics on TPUs wontfix This will not be worked on
#591 opened May 13, 2024 by jqhoogland
7
[Proposal] Setup unit tests to cover model configurations good first issue Good for newcomers testing A task that needs to be completed in order to improve the current test coverage.
#588 opened May 11, 2024 by bryce13950
1 task done
@curt-tigges
1
[Bug Report] Unable to Llama 3 70b on multigpu in 4bit bug Something isn't working complexity-high Very complicated changes for people to address who are quite familiar with the code
#569 opened May 3, 2024 by winglian
@bryce13950
7
[Question] Difference in gpt-neo-125m weights loading with huggingface from_pretrained and HookTransformers.from_pretrained
#557 opened Apr 27, 2024 by petezone
1
[Bug Report] Grokking demo currently broken in Colab bug Something isn't working demo Creating a demo or tutorial
#543 opened Apr 16, 2024 by bryce13950
1 task done
1
[Bug Report] Test coverage missing on add_hook in hook_points bug Something isn't working testing A task that needs to be completed in order to improve the current test coverage.
#540 opened Apr 15, 2024 by bryce13950
2
[Bug Report] Residual Stack Not Adding Up demo Creating a demo or tutorial documentation Improvements or additions to documentation
#523 opened Mar 22, 2024 by EitanGronich
1
ProTip! Add no:assignee to see everything that’s not assigned.