Implement and perform the interpretability analysis of the BigScience models
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
- pytorch, scikit-learn
- Domain
- ai, machine-learning
Research direction
Start by reviewing the linked BigScience models, interpretability papers, probing-classifier survey, and BERTology primer, then use the SentEval coding challenge to perform a diagnostic classification study of a GPT-like model. Discuss the analysis results with mentor @oserikov and define the final model coverage and interpretability results before proceeding.
Written by the indexing model from the issue text.
Description
duration: scalable, can be both 175 and 350 hours
mentor: @oserikov
difficulty: easy
requirements:
- pytorch
- sklearn
- experience with re-using the academic code
- experience with Transformer Language models
useful links:
- Models produced by BigScience
- BigScience Interpretability papers curated list
- Survey on probing classifiers
- A Primer on Bertology
Idea Description:
During the season 2021/22, the BigScience team reached several crucial milestones by producing large-scale transformer language models. Some of them even come with the training checkpoints archived, thus allowing to study the emergence of the structures in language models. During this task, we propose to cover the released models with the supplementary interpretability information by applying classical XAI and probing methods described in the attached papers.
Coding Challenge
To better feel what the interpretability work looks like, we ask you to perform a diagnostic classification study of the GPT-like language model, using the SentEval data. Reach out to mentors as soon as possible to discuss the analysis results.
- Dominant language
- No language data
- Stars
- 1
- Forks
- 1
- PR merge metrics
- No merged PRs in 30d
Contributor guide
No contributing guide indexed for this repository
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
-
Difficulty 2/5 1-3 hours Newbie friendliness 80/100
microsoft/magentic-ui#588 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
confident-ai/deepteam#289 ·
-
awaiting-response backend bug enhancement P1 platform/linux platform/macos qa safety
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
melgarafael/DeskcommCRM#1591 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 75/100