This respository is a Multi-Backend (Pytorch, Tensorflow, Jax) implementation of LLaMA using Keras3.
Base on LLaMA-Lite.
Implement the KVCache in simple code. Speed up the GPT
Easy to convert to tflite.
python performence.py-
Notifications
You must be signed in to change notification settings - Fork 0
zqgong/Llama2_keras3
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Llama2 of keras3 version
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published