Quantization made by Richard Erkhov.
This model is TOTALLY CONTAMINATED, which made resulting model unreliable.
SO DO NOT USE THIS MODEL FOR ANY PURPOSE.
PLEASE ONLY USE FOR REFERENCE.
This model is trained with
ultrachat_200k data to have conversational features.
This model was initialized with
Mistral-7B-v0.1Users and sponsors should be wary that many models are also unreliable. I hope our model can show the vulnerablity of the leaderboard.
