Skip to content
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

fix: Always return a list of quantization bits values from get_quantization #3926

Merged
merged 3 commits into from
Feb 9, 2024

Conversation

jeffkinnison
Copy link
Contributor

ludwig.utils.config_utils.get_quantization returns the value of quantization.bits for LLM model types (either int or None type), but for ECD it returns a list of values to account for multiple LLM encoders. To simplify checking the quantization, get_quantization now returns a list in every case.

Copy link

github-actions bot commented Feb 9, 2024

Unit Test Results

  4 files  ±0    4 suites  ±0   9m 25s ⏱️ -17s
12 tests ±0    9 ✔️ ±0    3 💤 ±0  0 ±0 
40 runs  ±0  28 ✔️ ±0  12 💤 ±0  0 ±0 

Results for commit b958a34. ± Comparison against base commit 51f38c5.

♻️ This comment has been updated with latest results.

@geoffreyangus geoffreyangus merged commit 9f3dbdc into master Feb 9, 2024
15 of 18 checks passed
@geoffreyangus geoffreyangus deleted the post-training-quant-fix branch February 9, 2024 21:06
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants