adelwolf5/YAM-AI-4B
VISIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.9BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 12, 2026Architecture:Transformer Featherless Exclusive Cold
adelwolf5/YAM-AI-4B is a 7.9 billion parameter multilingual assistant model fine-tuned from google/gemma-4-E4B-it. It features multilingual identity training across 80 languages, demonstrating successful performance in French, English, German, Arabic, Spanish, Italian, Russian, Japanese, Chinese, Korean, and Kabyle. This model is optimized for conversational AI applications requiring broad language support.
Loading preview...
YAM AI 4B: Multilingual Assistant
YAM AI 4B is a 7.9 billion parameter multilingual assistant model developed by adelwolf5. It is built upon the google/gemma-4-E4B-it base model, leveraging its capabilities through LoRA fine-tuning, with the LoRA layers subsequently merged into the base model.
Key Capabilities
- Multilingual Identity Training: The model has undergone specific identity training across 80 different languages, enhancing its ability to understand and respond appropriately in diverse linguistic contexts.
- Broad Language Support: It has been successfully tested and confirmed to perform effectively in a wide array of languages, including French, English, German, Arabic, Spanish, Italian, Russian, Japanese, Chinese, Korean, and Kabyle.
- Assistant Functionality: Designed as an intelligent assistant, it can engage in conversational interactions, as demonstrated by its self-identification as "YAM AI, an intelligent assistant."
Good For
- Multilingual Chatbots: Ideal for applications requiring conversational AI that can operate across numerous languages with consistent identity.
- Global User Support: Suitable for systems needing to interact with users from various linguistic backgrounds.
- Language-Diverse Applications: Any use case where a single model needs to handle prompts and generate responses in a broad spectrum of languages.