Missing tokenizer.model
#2
by
Aryanne
- opened
Loading model file /storage/emulated/0/amodels/silm/pytorch_model.bin
vocabtype: spm
Traceback (most recent call last):
File "/data/data/com.termux/files/home/llamaggml/convert.py", line 1326, in <module>
main()
File "/data/data/com.termux/files/home/llamaggml/convert.py", line 1314, in main
vocab = load_vocab(vocab_dir, args.vocabtype)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/data/com.termux/files/home/llamaggml/convert.py", line 1248, in load_vocab
raise FileNotFoundError(
FileNotFoundError: Could not find tokenizer.model in /storage/emulated/0/amodels/silm or its parent; if it's in another directory, pass the directory as --vocab-dir
I think idk how to quantize it.
Oh, sorry but I also don't know how to fix that..
no problem, I thought I could quantize, but at the moment there is no easy way to quantize it using llama.cpp, because it's a gptneox model
Aryanne
changed discussion status to
closed