[!NOTE]
→ There is an updated version of this model available, please see Good Robot 2 →.
The model "Good Robot" had one simple goal in mind: to be a good instruction-following model that doesn't talk like ChatGPT.
Built upon the Mistral 7b base, this model aims to provide responses that are as human-like as possible, thanks to some DPO training using the (for now, private) minerva-ai/yes-robots-dpo dataset.
HuggingFaceH4/no-robots was used as the base for generating a custom dataset to create DPO pairs.
It should follow instructions and be generally as smart as a typical Mistral model - just not as soulless and full of GPT slop.
Prompt Format:
Alpaca, my beloved ❤️
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{your prompt goes here}
### Response:
While I did my best to minimize GPTisms, no model is perfect, and there may still be instances where the generated content has GPT's common phrases - I have a suspicion that's due to them being engrained into Mistral model itself.
