not able to quantize after fine tuning

[geniusalert]

i am not able to quantize and getting this error
FileNotFoundError: Could not find tokenizer.model in llama-2-7b-meditext or its parent; if it's in another directory, pass the directory as --vocab-dir
ggml_init_cublas: found 1 CUDA devices:
Device 0: Tesla T4, compute capability 7.5
what do i do?

[mlabonne]

The repo you're trying to use doesn't have a tokenizer. It probably uses Llama 2's tokenizer. You can grab these three tokenizer* files from this repo: https://huggingface.co/meta-llama/Llama-2-7b-hf/tree/main and add them to yours.

[imran0x]

i am not able to quantize and getting this error FileNotFoundError: Could not find tokenizer.model in llama-2-7b-meditext or its parent; if it's in another directory, pass the directory as --vocab-dir ggml_init_cublas: found 1 CUDA devices: Device 0: Tesla T4, compute capability 7.5 what do i do?

Great