tokyotech-llm / Llama-3.1-Swallow-8B-v0.5

Other8B1.4K9Updated Jul 1, 2025

Downloads

1.4K

Likes

9

Last updated

Jul 1, 2025

License

llama3.3gemma

Llama 3.1 Swallow v0.5 is a large language model (8B) that was built by continual pre-training on the Meta Llama 3.1 model. Llama 3.1 Swallow v0.5 enhanced the Japanese language and reasoning(code & math) capabilities of the original Llama 3.1 while retaining the English langu…

Tags

  • llama
  • en
  • ja

Technical specifications

Parameters8B
LibraryNot available
Languagesen, ja
Licensellama3.3gemma