---
license: apache-2.0
---

GPTQ 4-bit no actor version for compatibility that works in textgen-webui

Generated by using scripts from https://gitee.com/yhyu13/llama_-tools

Original weight : https://huggingface.co/project-baize/baize-v2-7b

Baize is a lora training framework that allows fine-tuning LLaMA models on commondity GPUs.

Checkout my 13B Baize gptq 4bit here : https://huggingface.co/Yhyu13/baize-v2-13b-gptq-4bit

This model has an interesting behavior of generating further questions that help the conversation going. You can simply hit "Continue" and the chat goes all by itself

![img](./img/sample.png)