Edit model card

This is a 8.0bpw h8 quantized version of xingyaoww/CodeActAgent-Mistral-7b-v0.1. It is quantized with exllamav2.

Downloads last month
16
Inference API
Input a message to start chatting with DrNicefellow/CodeActAgent-Mistral-7b-v0.1-8bpw-h8.
This model can be loaded on Inference API (serverless).

Dataset used to train DrNicefellow/CodeActAgent-Mistral-7b-v0.1-8bpw-h8