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

AwqConfig class #132

Merged
merged 9 commits into from
Oct 31, 2023
Merged

AwqConfig class #132

merged 9 commits into from
Oct 31, 2023

Conversation

casper-hansen
Copy link
Owner

@casper-hansen casper-hansen commented Oct 30, 2023

This PR is created to make any new AutoAWQ model automatically compatible with transformers following the PR to merge AutoAWQ inference into the core of transformers: huggingface/transformers#27045.

  • Creates AwqQuantConfig that separates all the loading and saving from the base AWQ class.
  • Saves both quant_config.json and puts the quantization_config key directly into config.json
  • Inspired by AutoGPTQ's config class and Add quantconfig #91. Closes Create class QuantConfig  #8.

@casper-hansen casper-hansen merged commit eea08aa into main Oct 31, 2023
@casper-hansen casper-hansen deleted the new_config branch November 2, 2023 18:36
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.

Create class QuantConfig
1 participant