Shisa 7B: a new JA/EN bilingual model based on Mistral 7B

• llama.cpp

  769 56,891 10.0 C++

  LLM inference in C/C++

AWQ and GPTQ quants are available courtesy of (of course) TheBloke. There's no GGUF yet as I discovered something in llama.cpp's BPE tokenizer is seriously busted (affects many other Llama models w/ extended tokenizers), so track that bug if you want to see if that's fixed.

• google-research

  98 32,804 9.6 Jupyter Notebook

  Google Research

  

You could also try some dedicated translation models like https://huggingface.co/facebook/nllb-moe-54b (or https://github.com/google-research/google-research/tree/master/madlad_400 for something smaller) and see how they do.

• WorkOS

  workos.com sponsored

  The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.

  

Suggest a related project