Crystalcareai

Trying to replicate your results in training - but I'm running into vram issues - I believe the issue lies with my accelerate settings. Please advise.

This pull request implements support for InterLM2 in AutoAWQ. The integration has been successfully tested and generates high-quality output. **Changes include:** Added InterLM2 configurations to: models/init.py models/auto.py models/base.py Created a...

Hey @mlabonne, Hope you're well. Thanks, Lucas