Files
VicUnlocked-alpaca-30b/README.md
ModelHub XC 4ab48066de 初始化项目,由ModelHub XC社区提供模型
Model: Aeala/VicUnlocked-alpaca-30b
Source: Original Platform
2026-07-20 21:12:19 +08:00

19 lines
598 B
Markdown

## 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)