I get "error loading model: missing tok_embeddings.weight" with koboldcpp

#4
by whatnext - opened

Thank you for puplishing quantized model of ggml-q4_0-stablelm-tuned-alpha-7b.
I tested it with https://github.com/LostRuins/koboldcpp but it fails.
Would you please tell me how to run your model?
https://github.com/LostRuins/koboldcpp/issues/98

Sign up or log in to comment