Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / TransformerLensOrg/TransformerLens issues and pull requests
#666 - Fix attention result projection
Pull Request -
State: closed - Opened by callummcdougall 7 months ago
- 2 comments
#665 - [Proposal] Allow recent versions of beartype
Issue -
State: open - Opened by jettjaniak 7 months ago
- 6 comments
Labels: complexity-simple, tooling
#664 - [Question] Offline Error HookedTransformer.from_pretrained
Issue -
State: closed - Opened by pbernabeup 7 months ago
- 3 comments
#663 - Adding RMSNorm to apply_ln_to_stack
Pull Request -
State: closed - Opened by gaabrielfranco 7 months ago
- 1 comment
#662 - Add support for Qwen2 models
Pull Request -
State: closed - Opened by g-w1 7 months ago
- 3 comments
#661 - [Bug Report] Pythia output inconsistent across batch sizes when use_split_qkv_input=True
Issue -
State: open - Opened by oliveradk 7 months ago
Labels: bug, complexity-high, implementation-inaccuracy
#660 - removed einsum causing error when use_atten_result is enabled
Pull Request -
State: closed - Opened by oliveradk 7 months ago
- 2 comments
#659 - [Bug Report] Attn Result hook not working
Issue -
State: closed - Opened by oliveradk 7 months ago
- 2 comments
#658 - docs: update Main_Demo.ipynb
Pull Request -
State: closed - Opened by eltociear 7 months ago
- 1 comment
#657 - [Bug Report] RMSNormPre in Transformer_lens is maybe different from Llama source code?
Issue -
State: open - Opened by wangyifei0047 7 months ago
- 1 comment
Labels: complexity-moderate, needs-investigation
#656 - Release 2.2
Pull Request -
State: closed - Opened by bryce13950 7 months ago
#655 - Is it possible to use a locally downloaded model without accessing HF?
Issue -
State: closed - Opened by ccp123456 7 months ago
- 14 comments
#654 - Fix Out bias not being summed in attention component when using 4 bit precision
Pull Request -
State: closed - Opened by FlyingPumba 7 months ago
- 1 comment
#653 - [Question] loading Llama3-8B-instruct to HookedTransformer got a warning saying You are not using LayerNorm, so the writing weights can't be centered! Skipping!
Issue -
State: closed - Opened by wangyifei0047 7 months ago
- 1 comment
#652 - Mlp cleanup
Pull Request -
State: closed - Opened by bryce13950 7 months ago
#651 - [Bug Report] Phi-3 Model does not load on Transformer Lens
Issue -
State: closed - Opened by KanishkT123 8 months ago
- 3 comments
#650 - Added support for Gemma-2
Pull Request -
State: closed - Opened by neelnanda-io 8 months ago
- 11 comments
#649 - Model baichuan
Pull Request -
State: open - Opened by bryce13950 8 months ago
#648 - Fixed weight conversion
Pull Request -
State: closed - Opened by bryce13950 8 months ago
#647 - Move out pretrained weight conversions
Pull Request -
State: closed - Opened by richardkronick 8 months ago
#646 - Moved mixtral weights to another module
Pull Request -
State: closed - Opened by bryce13950 8 months ago
#645 - Match Huggingface GPT2 implementation *exactly*
Pull Request -
State: closed - Opened by joelburget 8 months ago
- 2 comments
#644 - [Proposal] Documentation: Map the Act Names to the Transformer
Issue -
State: open - Opened by JuVogt 8 months ago
- 3 comments
Labels: documentation, complexity-moderate
#643 - Add tests for ActivationCache
Pull Request -
State: closed - Opened by FlyingPumba 8 months ago
- 5 comments
#642 - Steering vanilla GPT2 with SAE vectors based on transformerlens version of GPT2
Issue -
State: closed - Opened by ianand 8 months ago
- 3 comments
#641 - Match Huggingface MLP implementation exactly.
Pull Request -
State: closed - Opened by joelburget 8 months ago
- 2 comments
#640 - add better model properties table to docs
Pull Request -
State: closed - Opened by mivanit 8 months ago
- 1 comment
#639 - add tests for Attention
Pull Request -
State: closed - Opened by anthonyduong9 8 months ago
#638 - Add tests for gated mlp
Pull Request -
State: closed - Opened by anthonyduong9 8 months ago
- 1 comment
#637 - Add comparing-to-huggingface.ipynb.
Pull Request -
State: closed - Opened by joelburget 8 months ago
#636 - Fix typo in Main_Demo.ipynb
Pull Request -
State: closed - Opened by ianand 8 months ago
#635 - Add skip_verbose_naming in add_hook to give an option for skipping the naming
Pull Request -
State: closed - Opened by verlocks 8 months ago
#634 - Release 2.1
Pull Request -
State: closed - Opened by bryce13950 8 months ago
#633 - Move out pretrained weight conversion functions
Pull Request -
State: closed - Opened by richardkronick 8 months ago
- 2 comments
#632 - Lock datasets version
Pull Request -
State: closed - Opened by courtney-sims 8 months ago
- 1 comment
#631 - [Proposal] Remove the overhead caused by full_hook.__name__ = (hook.__repr__())?
Issue -
State: closed - Opened by verlocks 8 months ago
- 2 comments
#630 - Update README links to ARENA mech interp tutorials
Pull Request -
State: closed - Opened by gileshd 8 months ago
- 1 comment
#629 - NanoGPT Conversation did not handle case when there were no biases in model
Pull Request -
State: open - Opened by dashstander 8 months ago
- 1 comment
#628 - Refactor the utilities file into utilities folder
Pull Request -
State: closed - Opened by starship006 8 months ago
- 3 comments
#627 - Model config tests
Pull Request -
State: open - Opened by curt-tigges 8 months ago
- 1 comment
#626 - v2.0.1
Pull Request -
State: closed - Opened by bryce13950 8 months ago
#625 - Fix demos pip install packages from unfound repos
Pull Request -
State: closed - Opened by anthonyduong9 8 months ago
- 1 comment
#624 - [docs] Update Mixtral repo reference
Pull Request -
State: closed - Opened by joelburget 8 months ago
#623 - Unit tests loading from pretrained fill missing keys
Pull Request -
State: closed - Opened by richardkronick 8 months ago
- 1 comment
#622 - [Proposal] Add support for Baichuan1 and Baichuan2
Issue -
State: open - Opened by StarrySeas1 8 months ago
- 3 comments
Labels: complexity-moderate
#621 - [Bug Report] Getting `ModuleNotFoundError` when running `Grokking_Demo.ipynb`
Issue -
State: closed - Opened by anthonyduong9 9 months ago
- 2 comments
#620 - added news link
Pull Request -
State: closed - Opened by bryce13950 9 months ago
#619 - Fix llama demos
Pull Request -
State: closed - Opened by bryce13950 9 months ago
#618 - added release blog
Pull Request -
State: closed - Opened by bryce13950 9 months ago
#617 - Add tests for hook point add hook
Pull Request -
State: closed - Opened by anthonyduong9 9 months ago
- 1 comment
#616 - fixed format
Pull Request -
State: closed - Opened by bryce13950 9 months ago
#615 - [Bug Report] The output from HookedTransformer is not identical compared to Huggingface model for Lllama 3
Issue -
State: open - Opened by iamsimha 9 months ago
- 12 comments
Labels: bug, complexity-high
#614 - v1.19
Pull Request -
State: closed - Opened by bryce13950 9 months ago
#613 - moved enable hook functionality to separate functions and tested new functions
Pull Request -
State: closed - Opened by bryce13950 9 months ago
#612 - [Proposal] Merge utils and utilities
Issue -
State: closed - Opened by bryce13950 9 months ago
- 1 comment
Labels: complexity-moderate, refactor
#611 - [Bug Report] Missing `.items()` in `HookedRootModule.hooks`
Issue -
State: closed - Opened by dtch1997 9 months ago
- 4 comments
Labels: bug, complexity-simple, needs-investigation
#610 - add n k v heads to model properties table
Pull Request -
State: closed - Opened by anthonyduong9 9 months ago
- 3 comments
#609 - More pytest fixtures
Pull Request -
State: closed - Opened by bmillwood 9 months ago
#608 - 1.18 update
Pull Request -
State: closed - Opened by bryce13950 9 months ago
#607 - (v3) Draft PR: add Pyright static typing to hook_points.py #590
Pull Request -
State: closed - Opened by starship006 9 months ago
- 3 comments
#606 - Add support for ai-forever/mGPT model
Pull Request -
State: closed - Opened by SeuperHakkerJa 9 months ago
- 1 comment
#605 - Encoder-Decoder (T5) support
Pull Request -
State: closed - Opened by somvy 9 months ago
- 6 comments
#604 - Support for T5 models
Pull Request -
State: closed - Opened by somvy 9 months ago
#603 - Add support for model_name-less models.
Pull Request -
State: open - Opened by ArthurConmy 9 months ago
- 1 comment
#602 - Release 1.18
Pull Request -
State: closed - Opened by bryce13950 9 months ago
#601 - Release 1.18
Pull Request -
State: closed - Opened by bryce13950 9 months ago
#600 - removed Hooked SAE
Pull Request -
State: closed - Opened by bryce13950 9 months ago
#599 - Make `FactoredMatrix` compatible with tensor-like arguments
Pull Request -
State: open - Opened by JasonGross 9 months ago
- 1 comment
#598 - Run GitHub CI on MacOS
Pull Request -
State: open - Opened by bmillwood 9 months ago
- 5 comments
#597 - allow user to force trust_remote_code=true via from_pretrained kwargs
Pull Request -
State: closed - Opened by Butanium 9 months ago
- 1 comment
#596 - Update Gemma to reflect upstream HF changes
Pull Request -
State: closed - Opened by cmathw 9 months ago
- 1 comment
#595 - [Feature Request] Add Stopping Criteria support
Issue -
State: open - Opened by Butanium 9 months ago
- 2 comments
Labels: enhancement, complexity-high
#594 - [Bug Report] Updates to Gemma
Issue -
State: closed - Opened by cmathw 9 months ago
#593 - [Bug Report] First google search result for transformer lens is a 404
Issue -
State: closed - Opened by FabienRoger 9 months ago
- 3 comments
#592 - Setup for fine tuned Mistral model ?
Issue -
State: closed - Opened by SiddhantOjha17 9 months ago
- 8 comments
Labels: question
#591 - [Bug Report] TransformerLens's use of `einsum` leads to different training dynamics on TPUs
Issue -
State: closed - Opened by jqhoogland 9 months ago
- 9 comments
Labels: wontfix
#590 - (v2) Draft PR: add Pyright static typing to hook_points.py
Pull Request -
State: closed - Opened by starship006 9 months ago
- 11 comments
#589 - Interactive neuroscope ci
Pull Request -
State: closed - Opened by bryce13950 9 months ago
#588 - [Proposal] Setup unit tests to cover model configurations
Issue -
State: open - Opened by bryce13950 9 months ago
- 1 comment
Labels: good first issue, testing
#587 - Mistral 7b v0.2
Pull Request -
State: open - Opened by bryce13950 9 months ago
#586 - Revert "Add Mistral 7B v0.2 Instruct"
Pull Request -
State: closed - Opened by bryce13950 9 months ago
#585 - Fix docs badge in README
Pull Request -
State: closed - Opened by ArthurConmy 9 months ago
#584 - Add `.from_pretrained` to HookedSAE
Pull Request -
State: closed - Opened by ArthurConmy 9 months ago
- 2 comments
#583 - updated PR template to add a note about merging from different branches
Pull Request -
State: closed - Opened by bryce13950 9 months ago
#582 - Release 2.0
Pull Request -
State: closed - Opened by bryce13950 9 months ago
#581 - updated pull reqeust template to account for new dev branch
Pull Request -
State: closed - Opened by bryce13950 9 months ago
#580 - updated repo URL throughout the project
Pull Request -
State: closed - Opened by bryce13950 9 months ago
#579 - Add Mistral 7B v0.2 Instruct
Pull Request -
State: closed - Opened by fakerybakery 9 months ago
- 4 comments
#578 - Fix Pos Slice Issue
Pull Request -
State: closed - Opened by hannamw 9 months ago
- 3 comments
#577 - unwrapped config
Pull Request -
State: closed - Opened by bryce13950 9 months ago
#576 - Refactor integration tests
Pull Request -
State: closed - Opened by bryce13950 9 months ago
#575 - [Bug Report] Can't run the 4-bit quantized Llama-2 demo
Issue -
State: closed - Opened by atlaie 9 months ago
- 10 comments
Labels: bug, complexity-moderate
#574 - [Bug Report] Bug in `get_caching_hooks` when `pos_slice=None`
Issue -
State: closed - Opened by hannamw 9 months ago
- 3 comments
#573 - Add support for Phi-3
Pull Request -
State: closed - Opened by slash3g 9 months ago
- 6 comments
#572 - Fix broken HookedSAETransformer demo links
Pull Request -
State: closed - Opened by ckkissane 9 months ago
- 2 comments
#571 - added convenience function for unwrapping config to replace commonly …
Pull Request -
State: closed - Opened by bryce13950 9 months ago
#570 - [Bug Report] Mixtral generates nonsense
Issue -
State: closed - Opened by joelburget 9 months ago
- 42 comments
#569 - [Bug Report] Unable to Llama 3 70b on multigpu in 4bit
Issue -
State: open - Opened by winglian 10 months ago
- 8 comments
Labels: bug, complexity-high, multi-gpu
#568 - added debug step
Pull Request -
State: closed - Opened by bryce13950 10 months ago
#567 - Othello ci
Pull Request -
State: closed - Opened by bryce13950 10 months ago