## Fresh Alpasta, done Al Dente!
It's da *logical* choice! Now with a similar personality emulation quality to [GPT4-X-Alpasta-30b!](https://huggingface.co./MetaIX/GPT4-X-Alpasta-30b)

## Model Info:
ChanSung's [Alpaca-LoRA-30B-elina](https://huggingface.co./LLMs/Alpaca-LoRA-30B-elina) merged with [Open Assistant's second Finetune](https://huggingface.co./OpenAssistant/oasst-sft-7-llama-30b-xor)

## Benchmarks:
**Wikitext2:** 4.662261962890625

**PTB:** 24.547462463378906

**C4:** 7.05504846572876

[4bit](https://huggingface.co./Aeala/GPT4-x-AlpacaDente2-30b/blob/main/4bit.safetensors):

**Wikitext2:** 5.016242980957031

**PTB:** 25.576189041137695

**C4:** 7.332120418548584	

~ Thanks to [askmyteapot](https://huggingface.co./askmyteapot) for performing these benchmarks!