metadata
license: apache-2.0
language:
- en
HamSter v0.1
A Uncensored fine tune model roleplay focused of mistralai/Mistral-7B-v0.2... With the help of my team.
- For good performance i recommend you to use a detailled character card! Check out Chub.ai (There might be nsfw content on the homepage) for some premade character card
- Uses Llama2 prompt template also in chat-instruct mode.
I had good results with this parameters:
- temperature: 0.8
- top_p: 0.75
- min_p: 0
- top_k: 0
- repetition_penalty: 1.05
RolePlay Test
BenchMarks on OpenLLM Leaderboard
More details: HamSter-0.1 OpenLLM BenchMarks
BenchMarks on Ayumi's LLM Role Play & ERP Ranking
More details: Ayumi's LLM RolePlay & ERP Rankin HamSter-0.1 GGUF version Q6_K
