OpenLLM
OpenLLM copied to clipboard
output "killed" with nothing else
I tried use OpenLLM with my merged Llama model, and it print two lines of "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.", and then, KILLED.
Then I used just llama model, and it just print KILLED
is anything I did wrong?
python 3.9 cuda 11.8
what version of openllm is this?
close for openllm 0.6