A 22B model merge by grimpep mixing 13Bv2-llama-modelmerge with Wizard-Vicuna-30B-Superhot-8K.
Please see the original repo for further information.

From my brief testing this model works great for chat or roleplaying using Llama2 syntax along with SimpleProxy or SimpleProxy style prompt instruction.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model's library.