BASE MODEL: mistralai/Mistral-Small-24B-Base-2501 LICENSE: apache-2.0 LANGUAGE: English CONTEXT LENGTH: 32768 tokens

TEMPERATURE: 1.2 MIN_P: 0.05 (Everything Else Neutral MEME Samplers Too.)

<|im_start|>system system prompt<|im_end|> <|im_start|>user Hello, WinterEngine!<|im_end|> <|im_start|>assistant Hello! How can I help you today?<|im_end|>

I-mat: https://huggingface.co/mradermacher/WindEngine-24B-Instruct-i1-GGUF Normal: https://huggingface.co/mradermacher/WindEngine-24B-Instruct-GGUF

Big Thanks to mradermacher for the Quants.

You can ignore this if you want, but I just wanted to share something. I was trying to create a model that follows prompts well, stays uncensored, and brings a lot of creativity — especially with roleplay capabilities. Started out using the base 24B Instruct model — it was decent, but felt a bit dry and overly censored. So, I began testing and merging different models. Then found PersonalityEngine 24B, which followed instructions well and had solid roleplay potential, though it felt a little bland. Discovered Redemption Winds — much better at roleplay, but not as strong when it came to following instructions. After trying three different model merges, this pairing turned out to be the best combination. [The result? A model that follows instructions, excels at roleplay, and — for my single folks out there — works great for AI girlfriend roleplay, too.]