---
datasets:
- gozfarb/ShareGPT_Vicuna_unfiltered
---

## LoRA Info:
Please note that this is a highly experimental LoRA model. It may do some good stuff, it may be bad, it may do nothing and not work. Hopefully after training is fully done, it'll be good!

Current upload: checkpoint of epoch 1.0 (of 3)

The alpaca-lora repo by tloen doesn't *seem* to create an immediately working adapter/peft model until the training is finalized, but I attempted to turn a checkpoint into one.
I hope it works for y'all ^~^ Thanks to MetaIX for initial seemingly successful testing of the first uploaded checkpoint (epoch 0.8).

**Wikitext2 eval benchmark for epoch 0.8 upload:** 4.548329830169678 (Thanks to Metal/MetaIX)