|
--- |
|
datasets: |
|
- HuggingFaceH4/no_robots |
|
language: |
|
- en |
|
license: cc-by-nc-4.0 |
|
--- |
|
|
|
# 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 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](https://huggingface.co/kubernetes-bad/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](https://huggingface.co/Gryphe). |
|
|
|
## Training Data: |
|
- [HuggingFaceH4/no_robots](https://huggingface.co/datasets/HuggingFaceH4/no_robots) |
|
- [MinervaAI/yes-robots-dpo](https://huggingface.co/MinervaAI) |
|
- 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 |
|
|
