oxalis-ink/shamrock-0-e2b
shamrock-0-e2b is a 5.1 billion parameter language model developed by Oxalis, fine-tuned from Google DeepMind's Gemma 4 E2B. It is specifically optimized for language-learning applications within the Oxalis desktop app, focusing on Japanese, Korean, and Simplified Chinese for tasks like camera translation, text translation, tutoring, and dictionary functions. This model is designed for a 32768 token context length and is primarily intended for non-commercial use within its specialized domain.
Loading preview...
Overview
shamrock-0-e2b is a 5.1 billion parameter language model developed by Oxalis, fine-tuned from Google DeepMind's Gemma 4 E2B. It is specifically designed for integration into the Oxalis desktop app, enhancing language-learning surfaces for Japanese, Korean, and Simplified Chinese. This model is optimized for tasks such as camera translation, text translation, tutoring, and dictionary lookups.
Key Capabilities
- Specialized Language Learning: Fine-tuned for specific language-learning functionalities within the Oxalis app.
- Multilingual Focus: Optimized for Japanese, Korean, and Simplified Chinese.
- Gemma 4 E2B Base: Built upon Google DeepMind's Gemma 4 E2B architecture.
- Multi-Token Prediction (MTP) Drafter: Includes an MTP drafter for speculative decoding, available in GGUF and HF formats.
Good For
- Oxalis Desktop App Integration: Ideal for developers working with or extending the Oxalis language-learning application.
- Non-Commercial Language Learning Research: Suitable for personal projects and research in language education, particularly for the specified languages.
Important Note
This fine-tune is explicitly stated to perform poorly outside of its intended use within the Oxalis app. It is licensed under CC BY-NC 4.0, permitting non-commercial use with attribution. Commercial use requires specific licensing from Oxalis.