s3nh

/

internlm-internlm-chat-7b-GGUF

like 0

It cannot loaded by llama.cpp
error message:

GGML_ASSERT: D:\a\llama-cpp-python-cuBLAS-wheels\llama-cpp-python-cuBLAS-wheels\vendor\llama.cpp\llama.cpp:2349: codepoints_from_utf8(word).size() > 0

I converted it myself and get the same result (as well as internlm 1.1)