Closed rcontesti closed 1 week ago
Llama.cpp has proven quite convininent for many of us, I wish you could add the possibility of taking those models as inputs. Many thanks!
@rcontesti - we have a work-in-progress prototype to convert fp16/fp32 version of llama
https://github.com/pytorch/executorch/tree/main/extension/gguf_util
Once again many thanks @mergennachin
Llama.cpp has proven quite convininent for many of us, I wish you could add the possibility of taking those models as inputs. Many thanks!