Model Info
Merge of my 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