Illegal instruction with llama_cpp_python-0.2.11
#1
by
vasilee
- opened
my code is
from llama_cpp import Llama
llm = Llama(model_path="./models/causallm_7b.Q4_K_S.gguf",
verbose=True, n_ctx=4096)
Apologies, the originally uploaded GGUFs had an error. Please try re-downloading; the newly uploaded GGUFs are confirmed to work with latest llama.cpp. I've not tested them with llama-cpp-python, but I would hope they should work there too.
thank you,
it works with the latest llama.cpp, but not with llama_cpp_python (yet)