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

#736 - Upstream update

Pull Request - State: closed - Opened by bryce13950 6 days ago

#735 - Release 2.7

Pull Request - State: closed - Opened by bryce13950 6 days ago

#734 - Model llama 3.2

Pull Request - State: closed - Opened by bryce13950 6 days ago

#733 - `utils.test_prompt` compares multiple prompts

Pull Request - State: closed - Opened by bryce13950 6 days ago

#732 - Type hooked encoder

Pull Request - State: closed - Opened by bryce13950 6 days ago

#731 - Model llama 3.2

Pull Request - State: closed - Opened by bryce13950 6 days ago

#730 - Fine tune model and using this framework

Issue - State: open - Opened by nitay16 7 days ago

#729 - [Proposal] Guide to adding new models

Issue - State: open - Opened by deven367 7 days ago - 1 comment

#728 - `utils.test_prompt` compares multiple prompts

Pull Request - State: closed - Opened by callummcdougall 8 days ago - 12 comments

#727 - fixed typo

Pull Request - State: closed - Opened by bryce13950 9 days ago

#726 - [Proposal] Warn people when trying to load t5 into HookedTransformer

Issue - State: open - Opened by bryce13950 9 days ago - 4 comments
Labels: good first issue, complexity-simple

#724 - Load state dict with assign to avoid OOMs

Pull Request - State: open - Opened by cyber-chris 18 days ago - 4 comments

#723 - 2.6

Pull Request - State: closed - Opened by bryce13950 20 days ago

#722 - Redo of #713

Pull Request - State: closed - Opened by bryce13950 20 days ago

#721 - Release 2.5

Pull Request - State: closed - Opened by bryce13950 23 days ago

#720 - [Bug Report] Review current matmul function usages

Issue - State: open - Opened by bryce13950 23 days ago
Labels: bug, complexity-high

#719 - [Proposal] Add frequency-based RoPE support for Llama 3.1 models

Issue - State: open - Opened by frances720 24 days ago - 2 comments

#718 - Add `allenai/OLMoE-1B-7B-0924`.

Pull Request - State: open - Opened by joelburget 24 days ago - 2 comments

#717 - Allow loading only first n layers.

Pull Request - State: closed - Opened by joelburget 24 days ago

#716 - HookedTransformerConfig docs string: `weight_init_mode` => `init_mode`

Pull Request - State: closed - Opened by JasonGross 25 days ago - 1 comment

#715 - Fix typo in bug issue template

Pull Request - State: closed - Opened by JasonGross 25 days ago

#713 - Ungrouping GQA

Pull Request - State: closed - Opened by hannamw 27 days ago - 5 comments

#712 - v2.4.1

Pull Request - State: closed - Opened by bryce13950 28 days ago

#711 - support for the Amber model, including checkpoints

Pull Request - State: closed - Opened by tadakeigo 28 days ago

#710 - [Proposal] Add MVP Support For 1-2 Models Per-Modality

Issue - State: open - Opened by 4gatepylon about 1 month ago

#709 - [Bug Report] Gemma 2 unsupported?

Issue - State: closed - Opened by jasonlim131 about 1 month ago

#708 - [Bug Report] Gemma-2-2b not found

Issue - State: closed - Opened by jasonlim131 about 1 month ago - 1 comment

#706 - revised loading to recycle state dict

Pull Request - State: closed - Opened by bryce13950 about 1 month ago

#705 - Updated state loading to copy by reference

Pull Request - State: closed - Opened by bryce13950 about 2 months ago

#704 - [Proposal] Add support for TracrBench

Issue - State: open - Opened by HannesThurnherr about 2 months ago - 3 comments
Labels: new-architecture, complexity-high

#703 - Upstream commit update

Pull Request - State: closed - Opened by bryce13950 about 2 months ago

#702 - Release 2.4.0

Pull Request - State: closed - Opened by bryce13950 about 2 months ago

#701 - Release v2.3.1

Pull Request - State: closed - Opened by bryce13950 about 2 months ago

#700 - Recent release

Pull Request - State: closed - Opened by bryce13950 about 2 months ago

#699 - Improve attention masking

Pull Request - State: closed - Opened by UFO-101 about 2 months ago - 1 comment

#698 - Vram not used rtx 4090's

Issue - State: closed - Opened by mylesgoose about 2 months ago - 1 comment

#697 - How to get the Activation cache while the LLM is generating new tokens?

Issue - State: open - Opened by Meehaohao about 2 months ago - 2 comments
Labels: complexity-moderate

#696 - About the cached layernorm scale factors

Issue - State: open - Opened by Meehaohao about 2 months ago - 2 comments

#695 - Changed fold_value_biases method to be able to handle multi-gpu.

Pull Request - State: closed - Opened by Heigke about 2 months ago - 4 comments

#694 - Update Gemma2 attention scale

Pull Request - State: closed - Opened by mntss about 2 months ago - 4 comments

#693 - [Bug Report] Gemma-2-2b-it output logit doesn't match with huggingface

Issue - State: open - Opened by yeutong 2 months ago - 3 comments
Labels: complexity-high, implementation-inaccuracy

#692 - add a demo for Patchscopes and Generation with Patching

Pull Request - State: closed - Opened by HenryCai11 2 months ago - 2 comments

#691 - [Proposal] Add Lllama 3.1 support

Issue - State: open - Opened by ssuukk 2 months ago - 7 comments
Labels: new-architecture, complexity-moderate

#690 - Python 3.8 removal

Pull Request - State: closed - Opened by bryce13950 2 months ago

#689 - Added gemma-2 2b (#687)

Pull Request - State: closed - Opened by bryce13950 2 months ago

#688 - 2.3.0

Pull Request - State: closed - Opened by bryce13950 2 months ago

#687 - Added gemma-2 2b

Pull Request - State: closed - Opened by curt-tigges 2 months ago - 1 comment

#685 - [Bug Report] Different results from HuggingFace when using the GPT2 small example

Issue - State: open - Opened by nreHieW 2 months ago
Labels: complexity-high, needs-investigation, implementation-inaccuracy

#683 - [Bug Report] Qwen model implementation is too inaccurate

Issue - State: open - Opened by bryce13950 2 months ago - 3 comments
Labels: complexity-high, needs-investigation, implementation-inaccuracy

#682 - updated dependencies

Pull Request - State: open - Opened by bryce13950 2 months ago

#681 - Test arena cleanup

Pull Request - State: closed - Opened by bryce13950 2 months ago

#680 - [Proposal] Demo and Tutorial on Patchscopes and "Patching + Generation"

Issue - State: closed - Opened by HenryCai11 3 months ago - 5 comments
Labels: demo, complexity-moderate

#679 - NamesFilter can be a string

Pull Request - State: closed - Opened by jettjaniak 3 months ago - 1 comment

#678 - Add Mixtral to `test_match_huggingface` test

Pull Request - State: closed - Opened by joelburget 3 months ago - 1 comment

#677 - Fix typo in `embed.py` docs

Pull Request - State: closed - Opened by ArthurConmy 3 months ago

#675 - Release 2.2.2

Pull Request - State: closed - Opened by bryce13950 3 months ago

#674 - added arena content as a notebook

Pull Request - State: closed - Opened by bryce13950 3 months ago

#673 - fix: fixing broken backward hooks change

Pull Request - State: closed - Opened by chanind 3 months ago - 1 comment

#672 - [Bug Report] Backward hooks are broken as of v2.0.0

Issue - State: closed - Opened by chanind 3 months ago - 1 comment

#671 - [Proposal] Allow tied embeddings

Issue - State: open - Opened by neelnanda-io 3 months ago - 1 comment
Labels: enhancement, complexity-moderate

#670 - ValueError: microsoft/Phi-3-mini-128k-instruct not found.

Issue - State: open - Opened by joykirat18 3 months ago - 1 comment

#668 - Release 2.2.1

Pull Request - State: closed - Opened by bryce13950 3 months ago

#667 - [Bug Report] Einops shape error when `use_attn_result = True`

Issue - State: closed - Opened by dtch1997 3 months ago - 1 comment

#666 - Fix attention result projection

Pull Request - State: closed - Opened by callummcdougall 3 months ago - 2 comments

#665 - [Proposal] Allow recent versions of beartype

Issue - State: open - Opened by jettjaniak 3 months ago - 6 comments
Labels: complexity-simple, tooling

#664 - [Question] Offline Error HookedTransformer.from_pretrained

Issue - State: closed - Opened by pbernabeup 3 months ago - 3 comments

#663 - Adding RMSNorm to apply_ln_to_stack

Pull Request - State: closed - Opened by gaabrielfranco 3 months ago - 1 comment

#662 - Add support for Qwen2 models

Pull Request - State: closed - Opened by g-w1 3 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 3 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 3 months ago - 2 comments

#659 - [Bug Report] Attn Result hook not working

Issue - State: closed - Opened by oliveradk 3 months ago - 2 comments

#658 - docs: update Main_Demo.ipynb

Pull Request - State: closed - Opened by eltociear 3 months ago - 1 comment

#656 - Release 2.2

Pull Request - State: closed - Opened by bryce13950 3 months ago

#655 - Is it possible to use a locally downloaded model without accessing HF?

Issue - State: open - Opened by ccp123456 3 months ago - 9 comments

#654 - Fix Out bias not being summed in attention component when using 4 bit precision

Pull Request - State: closed - Opened by FlyingPumba 3 months ago - 1 comment

#652 - Mlp cleanup

Pull Request - State: closed - Opened by bryce13950 3 months ago

#651 - [Bug Report] Phi-3 Model does not load on Transformer Lens

Issue - State: closed - Opened by KanishkT123 3 months ago - 3 comments

#650 - Added support for Gemma-2

Pull Request - State: closed - Opened by neelnanda-io 3 months ago - 11 comments

#649 - Model baichuan

Pull Request - State: open - Opened by bryce13950 3 months ago

#648 - Fixed weight conversion

Pull Request - State: closed - Opened by bryce13950 3 months ago

#647 - Move out pretrained weight conversions

Pull Request - State: closed - Opened by richardkronick 3 months ago

#646 - Moved mixtral weights to another module

Pull Request - State: closed - Opened by bryce13950 3 months ago

#645 - Match Huggingface GPT2 implementation *exactly*

Pull Request - State: closed - Opened by joelburget 3 months ago - 2 comments

#644 - [Proposal] Documentation: Map the Act Names to the Transformer

Issue - State: open - Opened by JuVogt 3 months ago - 3 comments
Labels: documentation, complexity-moderate

#643 - Add tests for ActivationCache

Pull Request - State: closed - Opened by FlyingPumba 4 months ago - 5 comments

#641 - Match Huggingface MLP implementation exactly.

Pull Request - State: closed - Opened by joelburget 4 months ago - 2 comments

#640 - add better model properties table to docs

Pull Request - State: open - Opened by mivanit 4 months ago

#639 - add tests for Attention

Pull Request - State: closed - Opened by anthonyduong9 4 months ago

#638 - Add tests for gated mlp

Pull Request - State: closed - Opened by anthonyduong9 4 months ago - 1 comment

#637 - Add comparing-to-huggingface.ipynb.

Pull Request - State: closed - Opened by joelburget 4 months ago