| license: apache-2.0 | |
| language: | |
| - en | |
| # HamSter v0.2 | |
| A Uncensored fine tune model roleplay focused of [mistralai/Mistral-7B-v0.2](https://huggingface.co/mistralai/Mistral-7B-v0.2)... | |
| With the help of [my team](https://huggingface.co/ConvexAI). | |
| - For good performance i recommend you to use a detailled character card! Check out [Chub.ai](https://chub.ai) (There might be nsfw content on the homepage) for some premade character card | |
| - Uses Mistral prompt template with chat-instruct.` | |
| - It has been fine tune with a newer dataset :) | |
| - Next one will be better! | |
| ### I had good results with this parameters: | |
| - temperature: 0.27 | |
| - top_p: 0.95 | |
| - min_p: 0.05 | |
| - top_k: 30 | |
| - repetition_penalty: 1.185 | |
| ### Have Fun :) |