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.

Sign up for GitHub

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

Jump to bottom

INT4-AWQ PPL results for LLaMA-3 model are not as expected #257

Open
lisuying214 opened this issue Jan 23, 2025 · 0 comments
Open

INT4-AWQ PPL results for LLaMA-3 model are not as expected #257

lisuying214 opened this issue Jan 23, 2025 · 0 comments

Comments

@lisuying214
Copy link

lisuying214 commented Jan 23, 2025 •
edited
Loading

I keep following the new code. I have tried to evaluate both the real quantized model and pseudo quantization using Llama-3-8B-Instruct model (w4-g128), based on wikitext-2-raw-v1(test). But the PPL result is 8.5. (GPU:A100, test data is downloaded from https://huggingface.co/datasets/Salesforce/wikitext/tree/main/wikitext-2-raw-v1)
I want to confirm if my result is correct? And why are the results different?
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@lisuying214