Allow for external serving to be used with mmlu #99
Conversation
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
Merged
5 tasks
|
Note: Tests will fail until lm_eval 0.4.4 is available |
|
@JamesKunstle FYI |
jaideepr97
reviewed
Aug 19, 2024
|
cool patch btw! nice way to get around the current limitations |
The CI failures are because of requiring lm_eval 0.4.4. They are promising a new release should come out soon. We're in a holding pattern until then. |
|
@Mergifyio rebase |
Requires lm_eval >= 0.4.4 Signed-off-by: Dan McPherson <dmcphers@redhat.com>
✅ Branch has been successfully rebased |
mergify
bot
added
dependencies
alimaredia
approved these changes
Sep 6, 2024
nathan-weinberg
approved these changes
Sep 12, 2024
|
https://github.com/EleutherAI/lm-evaluation-harness/releases/tag/v0.4.4 has been released |
jaideepr97
approved these changes
Sep 12, 2024
mergify bot
added a commit
to instructlab/instructlab
that referenced
this pull request
Sep 25, 2024
…2065) Like with mt_bench, the new logic supports vllm and llama-cpp and passes the base url of the started instance to the mmlu library. This enables: - Consistency with how we are serving from a support perspective - Support for larger models with sharding across gpus - Multi-gpu support - Potential for faster performance with higher serving throughput Related: instructlab/eval#50 instructlab/eval#68 Corresponding Eval change: instructlab/eval#99 Resolves: #1792 **Checklist:** - [ ] **Commit Message Formatting**: Commit titles and messages follow guidelines in the [conventional commits](https://www.conventionalcommits.org/en/v1.0.0/#summary). - [ ] [Changelog](https://github.com/instructlab/instructlab/blob/main/CHANGELOG.md) updated with breaking and/or notable changes for the next minor release. - [ ] Documentation has been updated, if necessary. - [x] Unit tests have been added, if necessary. - [ ] Integration tests have been added, if necessary. Approved-by: nathan-weinberg Approved-by: alimaredia Approved-by: leseb
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Requires lm_eval >= 0.4.4
As implemented, if server_url is passed, it's used for external serving. Otherwise the old logic is still applied. Eventually we may want to remove the non external serving option.
Resolves: #50
Resolves: #68
Corresponding cli change: instructlab/instructlab#2065