-
Notifications
You must be signed in to change notification settings - Fork 603
Added evaluation script for qualcomm LlamaModel #11663
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Added evaluation script for qualcomm LlamaModel #11663
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11663
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit d4f2c9e with merge base 56392aa ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This pull request was exported from Phabricator. Differential Revision: D76634688 |
This PR needs a
|
This pull request was exported from Phabricator. Differential Revision: D76634688 |
Summary: Pull Request resolved: pytorch#11663 Script for evaluating models which follow qualcomm's LlamaModel definition, on lm eval harness tasks such as WikiText Results for WikiText evaluation task: | Model Name | max_seq_len | word_perplexity |----------|----------|----------| | Llama 1B Instruct | 128 | 34.82890030691187 | | Llama 1B Instruct | 512 | 22.919538703371582 | Differential Revision: D76634688
246afd1
to
74603d2
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thank you for adding the eval scripts. @shewu-quic @haowhsu-quic fyi we're adding eval scripts here and trying to improve the accuracy for ptq
Thank you, this is very helpful! |
This pull request was exported from Phabricator. Differential Revision: D76634688 |
Summary: Pull Request resolved: pytorch#11663 Script for evaluating models which follow qualcomm's LlamaModel definition, on lm eval harness tasks such as WikiText Results for WikiText evaluation task: | Model Name | max_seq_len | word_perplexity |----------|----------|----------| | Llama 1B Instruct | 128 | 34.82890030691187 | | Llama 1B Instruct | 512 | 22.919538703371582 | Reviewed By: cccclai Differential Revision: D76634688
74603d2
to
7596337
Compare
Summary: Pull Request resolved: pytorch#11663 Script for evaluating models which follow qualcomm's LlamaModel definition, on lm eval harness tasks such as WikiText Results for WikiText evaluation task: | Model Name | max_seq_len | word_perplexity |----------|----------|----------| | Llama 1B Instruct | 128 | 34.82890030691187 | | Llama 1B Instruct | 512 | 22.919538703371582 | Reviewed By: cccclai Differential Revision: D76634688
This pull request was exported from Phabricator. Differential Revision: D76634688 |
7596337
to
d4f2c9e
Compare
Differential Revision: D76634688 Pull Request resolved: pytorch#11663
Summary:
Script for evaluating models which follow qualcomm's LlamaModel definition, on lm eval harness tasks such as WikiText
Results for WikiText evaluation task:
Differential Revision: D76634688