Built upon the Mistral 7b 0.2 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.

Changes from the original good-robot model:

Mistral 7b-0.2 base (32k native context, no SWA)
ChatML prompt format
Trained using GaLore method

Prompt Format:

ChatML

<|im_start|>system
System message
<|im_start|>user
User message<|im_end|>
<|im_start|>assistant

Credits:

Model made in collaboration with Gryphe.

Training Data:

HuggingFaceH4/no_robots
MinervaAI/yes-robots-dpo
private datasets with common GPTisms

Limitations:

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.

License:

cc-by-nc-4.0

kubernetes-bad/good-robot-2

Good Robot 2 🤖

Prompt Format:

Credits:

Training Data:

Limitations:

License:

kubernetes-bad/
good-robot-2