The Llama-3.3-Swallow-70B-Instruct-v0.4 is a 70 billion parameter instruction-tuned large language model developed by tokyotech-llm, built upon Meta's Llama 3.3. This model specializes in enhancing Japanese language capabilities while maintaining strong English performance, achieved through continual pre-training on a diverse dataset including the Swallow Corpus Version 2. It is optimized for multi-turn dialogue and various Japanese and English tasks, making it suitable for applications requiring robust bilingual understanding and generation.
No reviews yet. Be the first to review!
Hugging Face