SDK-43: Add LLM unlearning models support#187
Merged
benglewis merged 28 commits intoJan 25, 2026
Merged
Conversation
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
benglewis
changed the title
This comment was marked as resolved.
This comment was marked as resolved.
This comment was marked as outdated.
This comment was marked as outdated.
Pun intended
…135M model is not a chat model
This comment was marked as resolved.
This comment was marked as resolved.
This comment was marked as outdated.
This comment was marked as outdated.
…sdk-43-add-support-for-unlearning-for-llm' into codex/2026-01-13/linear-mention-sdk-43-add-support-for-unlearning-for-llm
…sdk-43-add-support-for-unlearning-for-llm' into codex/2026-01-13/linear-mention-sdk-43-add-support-for-unlearning-for-llm
…upport-for-unlearning-for-llm # Conflicts: # tests/dataset_qa_shared.py
Python version was upgraded to Python 3.10 and new syntax can now be used
…un_by_id`) for unlearning LLM behavior
benglewis
requested review from
ddishi,
eayar123,
mishana and
shmuelyo
as code owners
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 17f756ef21
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
github-merge-queue
Bot
removed this pull request from the merge queue due to failed status checks
mishana
previously approved these changes
Jan 22, 2026
github-merge-queue Bot
pushed a commit
that referenced
this pull request
Jan 22, 2026
* Refine LLM unlearning models * Move `get_unique_id` to a new `testing_utils` file * Add small / Smol test Pun intended * Switch to `nvidia/Nemotron-Flash-1B` since it turns out that SmolLM2-135M model is not a chat model * Fix unlearning LLM run typing * Refine LLM run list typing * Type unlearning run list responses * Handle empty target utilities explicitly * Fix Ruff lint errors and basedpyright errors Python version was upgraded to Python 3.10 and new syntax can now be used * Add `check_run` and `acheck_run` (and `check_run_by_id` and `acheck_run_by_id`) for unlearning LLM behavior * Reduce duplicate code * LLM behavior unlearning test and loading of transformers Pipeline * Fix `numpy` version error * Fix requirements files * Fix retries when HTTP SSE request fails * Fix Misha's PR comment * Fix ChatGPT PR review comments * Fix Gemini's PR comment * Fix bug in `deleted_at` field for `OutputUnlearningLlmRun` Found while testing `.list()` * Rename `get_pipeline_for_run` to `get_hf_pipeline_for_run` * Fix `MODEL_FOR_IMAGE_TEXT_TO_TEXT_MAPPING_NAMES` being used instead of `MODEL_FOR_VISION_2_SEQ_MAPPING_NAMES` * Fix pydantic error due to class not really being imported at runtime
github-merge-queue
Bot
removed this pull request from the merge queue due to failed status checks
mishana
previously approved these changes
Jan 22, 2026
github-merge-queue
Bot
removed this pull request from the merge queue due to failed status checks
…M behavior unlearning Currently only `test2` does
mishana
approved these changes
Jan 22, 2026
github-merge-queue
Bot
removed this pull request from the merge queue due to failed status checks
mishana
previously approved these changes
Jan 25, 2026
mishana
approved these changes
Jan 25, 2026
benglewis
had a problem deploying
to
github-pages
GitHub Actions
Failure
benglewis
deleted the
codex/2026-01-13/linear-mention-sdk-43-add-support-for-unlearning-for-llm
branch
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Codex Task
Note
Introduces a typed LLM unlearning SDK surface and exports it.
hirundo/unlearning_llm.pyimplementingLlmModel(create/get/list/update/delete withfrom_responseparsing), model sources (HuggingFaceTransformersModel,LocalTransformersModel), and run orchestration viaLlmUnlearningRun(launch,cancel,rename,archive,restore,list)BiasBehavior,HallucinationBehavior,SecurityBehavior,CustomBehavior) and dataset descriptors for custom utilities__init__.pyand bump__version__to0.1.22Written by Cursor Bugbot for commit 28b6c1c. Configure here.