cuuupid / garden-state-llama

Llama-3-8B finetuned with ReFT to hyperfocus on New Jersey, the Garden State, the best state, the only state!

  • Public
  • 102 runs
  • GitHub
Run with an API
Playground API Examples README Train Versions

Input

Output

Run time and cost

This model runs on Nvidia A100 (80GB) GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

You can finetune your own Llama-3-8B with ReFT on the topic of your choice with as few as 6 data points and 100 epochs (~2 minutes) of training! Use the Train tab above to get going.

This uses pyreft and is largely based on the example provided there: stanfordnlp/pyreft