## Model Info
Merge of my [VicUnlocked-alpaca-half-30b LoRA](https://huggingface.co/Aeala/VicUnlocked-alpaca-half-30b-LoRA)

**Important Note**: While this is trained on a cleaned ShareGPT dataset like Vicuna used, this was trained in the *Alpaca* format, so prompting should be something like:

```
### Instruction:

<prompt> (without the <>)

### Response:
```

## Benchmarks
wikitext2: 4.372413635253906
ptb-new: 24.69171714782715
c4-new: 6.469308853149414

Results generated with GPTQ evals (not quantized) thanks to [Neko-Institute-of-Science](https://huggingface.co/Neko-Institute-of-Science)