https://huggingface.co/motexture/Cwen-7B-Instruct
#1248
by
Hamora
- opened
Hamora
changed discussion status to
closed
Unfortunately, it doesn't work with current versions of llama.cpp:
/llmjob/llama.cpp-cuda512/tools/imatrix/imatrix.cpp:911: GGML_ASSERT(!llama_vocab_get_add_eos(vocab)) failed