# Long Sequence Support

Ruri v3 is a general Japanese text embedding model based on ModernBERT-Ja, achieving industry-leading performance in Japanese text embedding tasks and supporting sequences up to 8192 tokens long.

Ruri v3 is a Japanese general text embedding model based on ModernBERT-Ja, achieving state-of-the-art performance in Japanese text embedding tasks, supporting sequences up to 8192 tokens.

This is an updated version of deberta-v2-xxlarge that implements the AutoModelForCausalLM class, enabling text generation. It fixes three issues in the original implementation, including the output embedding weight names, enhanced mask decoder implementation, and position embedding truncation handling.