-
Notifications
You must be signed in to change notification settings - Fork 395
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.
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
[Bug Report] Should we convert tensor dtype before eigenvalue decomposition
#934
opened May 30, 2025 by
notoookay
1 task done
[Bug Report] Error in loading Quantized Llama 3.2 Model from HuggingFace
#930
opened May 25, 2025 by
aditeyabaral
1 task done
[Question] Load model with supporting structure but different size
#929
opened May 21, 2025 by
xinranhe
[Question] Pythia models do not obtain act. name
blocks.0.hook_resid_mid in cache
#923
opened May 9, 2025 by
XiaoLeGG
[Bug Report] Issues with PosEmbed device when used with accelerate
#911
opened Apr 17, 2025 by
davidquarel
1 task done
[Bug Report] Device selection refactor (PR #864) breaks multi-GPU support
#907
opened Apr 6, 2025 by
mntss
1 task done
[Bug Report] Gemma model tensors initialized on CPU instead of GPU during state dictionary conversion
#904
opened Apr 3, 2025 by
joaoncardoso
1 task done
[Bug Report] some model weights are NaN when initializing
#902
opened Mar 27, 2025 by
mivanit
1 task done
[Proposal] Support Gemma 3
complexity-moderate
Moderately complicated issues for people who have intermediate experience with the code
enhancement
New feature or request
help wanted
Extra attention is needed
high-priority
Maintainers are interested in these issues being solved before others
model-request
Any issues related to requesting additional model support
new-architecture
This card involves adding a new architecture .
#898
opened Mar 19, 2025 by
neelnanda-io
[Proposal] Support R1 Distills
complexity-simple
Simple issues, which may be good for beginners
enhancement
New feature or request
help wanted
Extra attention is needed
high-priority
Maintainers are interested in these issues being solved before others
model-request
Any issues related to requesting additional model support
#897
opened Mar 19, 2025 by
neelnanda-io
[Proposal] Implement LongRoPE
complexity-moderate
Moderately complicated issues for people who have intermediate experience with the code
#894
opened Mar 10, 2025 by
YuhengHuang42
1 task done
Adapting a HookedTransformer to a model that is not part of the existing models
#888
opened Feb 27, 2025 by
Noam-Diamant
[Proposal] Add official support for device_map
complexity-high
Very complicated changes for people to address who are quite familiar with the code
#872
opened Feb 18, 2025 by
bryce13950
1 task done
[Question] How do I add a custom generative video transformer into TransformerLens?
complexity-high
Very complicated changes for people to address who are quite familiar with the code
#869
opened Feb 17, 2025 by
EmilRyd
[Question] Does TransformerLens support LVLM like Qwen2-VL?
complexity-moderate
Moderately complicated issues for people who have intermediate experience with the code
model-request
Any issues related to requesting additional model support
#867
opened Feb 13, 2025 by
Tizzzzy
[Bug Report] Prioritize Local hf_model.config for Qwen Models to Avoid Unnecessary Hugging Face API Calls
complexity-moderate
Moderately complicated issues for people who have intermediate experience with the code
high-priority
Maintainers are interested in these issues being solved before others
#846
opened Jan 30, 2025 by
yhr-code
1 task done
Previous Next
ProTip!
Adding no:label will show everything without a label.