pykoi-rlhf-finetuned-transformers

pykoi-rlhf-finetuned-transformers copied to clipboard

SFT for D2L + Pre-Training (rename of the previous SFT)

1

Implement SFT and use D2L as a demo case. Rename previous SFT to Pre-training and modify corresponding scripts/notebooks.

llauraa23

Currently, Pykoi documentation page looks a little weird in desktop mode. @jojortz 

vicshi06

Thanks so much for such a great repo. I was wondering if is there any support to attach our data file for RAG/RLHF chatbot?

NiloufarAb

use python 3.9 to 3.11 multiple versions

3

expand GitHub action file to support multiple python version builds.

jimexist

Added mlflow

4

Added draft example code to train with mlflow. It encountered some GPU issue. We can discuss it when we meet, maybe on Friday. This is not the final version, just...

larryyin