Noromaid built on top of Starling-LM-7B-alpha
Maywell’s PiVoT-0.1-Starling-LM-RP is based on berkeley-nest/Starling-LM-7B-alpha, which is based on OpenChat 3.5, and it does well at RP. I think Starling-LM-7B-alpha would work as a terrific base for Noromaid.
https://huggingface.co/maywell/PiVoT-0.1-Starling-LM-RP
https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha
https://huggingface.co/openchat/openchat_3.5
OPENCHAT 3.5:
🔥 The first 7B model Achieves Comparable Results with ChatGPT (March)! 🔥
🤖 #1 Open-source model on MT-bench scoring 7.81, outperforming 70B models 🤖
OpenChat is an innovative library of open-source language models, fine-tuned with C-RLFT - a strategy inspired by offline reinforcement learning. Our models learn from mixed-quality data without preference labels, delivering exceptional performance on par with ChatGPT, even with a 7B model. Despite our simple approach, we are committed to developing a high-performance, commercially viable, open-source large language model, and we continue to make significant strides toward this vision.
I got notified for this, and it seems like a good opportunity to shill my PivotMaid-Starling-11b, something that might work for your use case. Sorry if that's out of line.
No worries. I’ll give it a try. I’m always looking for new models to play with. Thanks🤘😁
This is not an official finetune so it will loose quality ofc, if you can show us that it is a good model in practise me way consider training on it.