You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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?
The text was updated successfully, but these errors were encountered:
geniusalert
changed the title
not able to quantize after fine tuning on colab
not able to quantize after fine tuning
Jan 4, 2024
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.
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?
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?
The text was updated successfully, but these errors were encountered: