---
datasets:
  - ewof/koishi-instruct-metharme
  - PygmalionAI/PIPPA
---

just testing for now, qlora marge

https://rentry.org/v43eo updated the rentry slightly


![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f38f3a89203d118da8b477/p2ThhxJ7-tkpf4E5OL3hc.png)

NousResearch/Llama-2-13b-hf tuned on koishi data (without code subsets)

then tuned on pippa

then tuned on limarp

all metharme format