DevWorld/Gemago-2b

TEXT GENERATIONConcurrency Cost:1Model Size:2.6BQuant:BF16Ctx Length:8kLicense:apache-2.0Architecture:Transformer0.0K Open Weights Cold

DevWorld/Gemago-2b is a 2.6 billion parameter, instruction-tuned causal language model developed by DevWorld, based on Google's Gemma architecture. This lightweight model is specifically fine-tuned for English-to-Korean and Korean-to-English translation tasks. It maintains Gemma's 8192-token context length, making it suitable for direct translation applications.

Loading preview...

Gemago-2b: A Specialized Translation Model

Gemago-2b, developed by DevWorld, is a 2.6 billion parameter language model built upon Google's Gemma architecture. Its primary focus is on providing efficient and accurate English-to-Korean and Korean-to-English translation capabilities. The model retains the 8192-token context length of the original Gemma base model.

Key Capabilities

  • Bidirectional Translation: Optimized for translating text between English and Korean.
  • Lightweight: At 2.6 billion parameters, it offers a balance of performance and resource efficiency.
  • Gemma-based: Leverages the foundational strengths of the Gemma model family.

Good For

  • Applications requiring direct English-Korean or Korean-English text translation.
  • Developers looking for a compact, specialized model for multilingual tasks involving these two languages.
  • Integration into systems where resource constraints are a consideration, due to its lightweight nature.