Quantise this model - missing file

#10
by cuh008 - opened

Hello, I would like to quantise this model using llama.cpp. For this the following file is required: tokenizer.model.
Can someone provide this file please?

LAION LeoLM org

You can find already quantized GGUF and AWQ versions of all our models on TheBloke's page: https://huggingface.co/TheBloke?search_models=leo . If you want to do quantization yourself, I suspect you can find the missing tokenizer.model also there :)

Sign up or log in to comment