Closed kouta-kun closed 9 months ago
This pull request modifies the bindings and build process to allow linking to the latest llama.cpp commit, in the process allowing the usage of LLaMAv2 and the new GGUF format. It has been tested with the following model: https://huggingface.co/TheBloke/Llama-2-7B-GGUF/blob/main/llama-2-7b.Q4_K_S.gguf
This pull request modifies the bindings and build process to allow linking to the latest llama.cpp commit, in the process allowing the usage of LLaMAv2 and the new GGUF format. It has been tested with the following model: https://huggingface.co/TheBloke/Llama-2-7B-GGUF/blob/main/llama-2-7b.Q4_K_S.gguf