gptqlora VS chathub

GPTQLoRA: Efficient Finetuning of Quantized LLMs with GPTQ (https://github.com/qwopqwop200/gptqlora/tree/main)

The difference from QLoRA is that GPTQ is used instead of NF4 (Normal Float4) + DQ (Double Quantization) for model quantization. The advantage is that you can expect better performance because it provides better quantization than conventional bitsandbytes. The downside is that it is a one-shot quantization methodology, so it is more inconvenient than bitsandbytes, and unlike bitsandbytes, it is not universal. I'm still experimenting, but it seems to work. At least, I hope it can be more options for people using LoRA. https://github.com/qwopqwop200/gptqlora/tree/main

Try ChatHub, it's a third party chatbot client which supports Bard, and have conversation history feature

ChatHub is an all-in-one chatbot client (https://github.com/chathub-dev/chathub/blob/main/README.md)

Try https://chathub.gg to find out.

ChatHub - Use ChatGPT, Bard, Bing & Claude in one app

Use ChatGPT, Bing, Bard, and Claude in one app with ChatHub (Link)

You can install ChatHub here: https://chathub.gg

ChatGPT, Bing, Bard, and Claude - Use different chatbots in one app with ChatHub. Users can compare chatbot answers and use ChatGPT's faster and more cost-effective API mode. The platform also features markdown, code highlight support, a prompt library, and much more. (Source)