Integrate existing tools: Captum, LIT, AllenNLP Interpret, NeuroX into the HF pipeline
Nobody has claimed this yet.
Assessment
- Difficulty
- 5/5
- Estimated time
- Over a week
- Newbie friendliness
- 20/100
- Issue type
- Feature
- Clarity
- Needs clarification
- Activity status
- Stale
- Tech stack
- python, pytorch, scikit-learn
- Domain
- ai, machine-learning
Research direction
Start with the Captum, AllenNLP Interpret, and NeuroX links and the Coding Challenge in task 1. Discuss which methods to select with the listed mentor before defining the HF-compatible aggregation API; done requires the chosen methods, an all-in-one interpret method, initial BigScience checkpoint analysis, and code that can support further methods.
Written by the indexing model from the issue text.
Description
duration: scalable, can be both 175 and 350 hours
mentor: @oserikov
difficulty: medium
requirements:
- pytorch
- sklearn
- python engineering code, with OOP and patterns
- experience with Transformer Language models
useful links:
Idea Description:
There exist lots of interpretability tools, both for Industry and Academia users.
While some of them are general-purpose, and the others are very field-specific, all of them have several things in common.
One would typically apply them to HuggingFace models. All of these methods try to explain the black-boxes we have.
What we propose is, shortly, to put together the existing popular models interpretation stack. We've made a survey of interpretability for LLMs and now have both scientific and engineering vision of what we should implement in order to maximize the interpretability of the existing LLMs.
You need to implement the HF-compatible interpretability aggregation API. The exact tasks to accomplish are:
- choose the most important methods provided by Captum, Interpret and NeuroX (which ones? to better understand the task, try to figure it out yourself. having done this, reach out to us ASAP and we will discuss your vision)
- implement the all-in-one interpret method to run all the chosen ones
- perform the initial analysis of the BigScience models checkpoints
- ensure the codebase is easy to cover the new methods
Coding Challenge
see task 1.
- Dominant language
- No language data
- Stars
- 1
- Forks
- 1
- PR merge metrics
- No merged PRs in 30d
Getting set up
We have not checked this project's setup files yet. Start from its README, and see our first-contribution guide for the general steps.
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from bigscience-workshop/interpretability-ideas
-
Difficulty 5/5 Over a week Newbie friendliness 20/100
-
Difficulty 5/5 Over a week Newbie friendliness 10/100
-
Difficulty 5/5 Over a week Newbie friendliness 20/100
-
Difficulty 5/5 Over a week Newbie friendliness 15/100
-
Difficulty 5/5 Over a week Newbie friendliness 10/100
All issues in bigscience-workshop/interpretability-ideas
Similar issues
-
area:ai-suggestions bug good first issue P2
Difficulty 2/5 1-3 hours Newbie friendliness 84/100
uttrflow/uttrflow-swift#1922 ·
Maintainers usually reply within 1 day
-
bug
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
Maintainers usually reply within 1 day
-
triage/confirmed
Difficulty 2/5 1-3 hours Newbie friendliness 86/100
agentscope-ai/agentscope#2876 ·
Maintainers usually reply within 1 day
-
Difficulty 1/5 Under an hour Newbie friendliness 72/100
e2b-dev/awesome-ai-agents#1643 ·
Maintainers usually reply within 1 day
-
Docs never explain image replay cost with native-vision models or the tools.media.models[] opt-outOpenclawsweeper:linked-pr-open clawsweeper:no-new-fix-pr impact:ux-friction issue-rating: 🌊 off-meta tidepool P2
Difficulty 2/5 1-3 hours Newbie friendliness 88/100
openclaw/openclaw#159202 · 1 comment · 1 reaction ·
Maintainers usually reply within 1 day