Quantizing pre-trained JAX model #3951
Unanswered
overseerlabs
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hi everyone, I'm trying to quantize a pre-trained JAX model (> 10GB). Is that currently possible with Flax? I tried converting to TF, since I know they support quantization, but started getting the 2GB flatbuffer hard limit exception. Let me know what you guys think, thanks!
Beta Was this translation helpful? Give feedback.
All reactions