Where can I find llama-embedding and llama-tokenize?

#1
by puppytag - opened

Your paper is great. It is a great job. But when I tried to use it myself. I found that I can not find llama-embedding and llama-tokenize in "https://github.com/hanxiao/llama.cpp".
I would be very grateful if you could take the time to answer my question.

Your paper is great. It is a great job. But when I tried to use it myself. I found that I can not find llama-embedding and llama-tokenize in "https://github.com/hanxiao/llama.cpp".
I would be very grateful if you could take the time to answer my question.

Hi @puppytag ,

I faced the same problem as you when trying to use the Jina Reranker v3 GGUF implementation. The llama-embedding and llama-tokenize binaries are not pre-built in the hanxiao/llama.cpp repository - you need to build them from source.

I've created a complete working implementation with detailed instructions in my repo.
please check https://github.com/ridwanputra888/jina_reranker_v3_gguf_fix

Sign up or log in to comment