eval script for llama #374
Merged
Conversation
This file contains 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
Summary: previously we were only doing this in the tests but now we have an eval script to along with generate.py Test Plan: python eval.py -q "int4wo-64-gptq" Reviewers: Subscribers: Tasks: Tags:
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/374
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit efb18ce with merge base bc2f8b7 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
msaroufim
reviewed
Jun 15, 2024
| @@ -0,0 +1,134 @@ | |||
| # Copyright (c) Meta Platforms, Inc. and affiliates. | |||
There was a problem hiding this comment.
Thanks! since this is not tested in CI mind just printing the expected output and putting it in the github issue description
There was a problem hiding this comment.
i added the values to the PR description
msaroufim
approved these changes
Jun 18, 2024
dbyoung18
pushed a commit
to dbyoung18/ao
that referenced
this pull request
Jul 31, 2024
* eval script for llama Summary: previously we were only doing this in the tests but now we have an eval script to along with generate.py Test Plan: python eval.py -q "int4wo-64-gptq" Reviewers: Subscribers: Tasks: Tags: * new api Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags:
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Outdated suggestions cannot be applied.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.
Summary: previously we were only doing this in the tests but now we have an eval script to along with generate.py
Test Plan:
python eval.py -q "int4wo-64-gptq"
expected results:
(using meta-llama/Llama-2-7b-chat-hf weights)
Base (bfloat16) | 12.212 |
int8dq | 12.262 |
int8wo | 12.204 |
int4wo-64 | 12.843 |
int4wo-64-GPTQ | 12.489
Reviewers:
Subscribers:
Tasks:
Tags: