tokyotech-llm/Swallow-13b-NVE-hf
TEXT GENERATIONConcurrency Cost:1Model Size:13BQuant:FP8Ctx Length:4kLicense:llama2Architecture:Transformer Open Weights Cold

The Swallow-13b-NVE-hf model by tokyotech-llm is a 13 billion parameter language model continually pre-trained from the Llama 2 family, specifically enhanced with Japanese language data. This NVE (No Vocabulary Expansion) version focuses on strong performance in Japanese tasks while maintaining English capabilities. It is designed for efficient processing of Japanese text, making it suitable for applications requiring robust Japanese language understanding and generation.

Loading preview...