Quantization #4

Open
opened 2024-12-05 10:13:22 +00:00 by james · 1 comment
Owner

We can give her a larger model and make her smarter!

We can give her a larger model and make her smarter!
james added the
enhancement
label 2024-12-05 10:13:22 +00:00
Author
Owner

Currently uses 4-bit quantization with load_in_4bit flag, and the RVC model is loaded in float16 format

Currently uses 4-bit quantization with load_in_4bit flag, and the RVC model is loaded in float16 format
Sign in to join this conversation.
No Milestone
No project
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: james/MikuAI#4
No description provided.