ayan4m1/Chise-7B
TEXT GENERATIONConcurrent Unit Cost:1Model Size:7BQuant:FP8Context Size:4kTool Calling:SupportedPublished:Mar 28, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
Chise-7B is a 7 billion parameter Mistral-based causal language model developed by ayan4m1, fine-tuned from unsloth/mistral-7b-instruct-v0.3-bnb-4bit. This model specializes in providing anime recommendations, having been trained on a scraped dataset from MyAnimeList. It is designed to suggest anime based on user preferences, offering a focused application for enthusiasts.
Loading preview...
Chise-7B: Anime Recommendation Model
Chise-7B, developed by ayan4m1, is a 7 billion parameter language model fine-tuned from unsloth/mistral-7b-instruct-v0.3-bnb-4bit. Its core specialization lies in generating anime recommendations.
Key Capabilities
- Anime Recommendation: The model has been specifically trained on a dataset of recommendations scraped from MyAnimeList, enabling it to provide relevant anime suggestions.
- Preference-Based Suggestions: Users can describe their anime preferences or list titles they enjoy, and Chise-7B will offer new recommendations.
Good For
- Anime Enthusiasts: Ideal for users seeking personalized anime suggestions.
- Recommendation Systems: Can be integrated into applications requiring a specialized anime recommendation engine.
Usage Notes
- Sampling Temperature: The developer suggests using a sampling temperature greater than 1.0 for optimal results, which can influence the diversity and creativity of the recommendations.