Add eval benchmarks

README.md

@@ -1,5 +1,14 @@
 ## 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)
+## 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
+
+~ Thanks to askmyteapot for performing this benchmark!