how to convert the safetensors to pth?
#30
by
goathacker
- opened
I do not find the script to do that conversion
python llama.py ../lmsys/vicuna-13b-v0 c4 --wbits 4 --true-sequential --groupsize 128 --save vicuna-13b-4bit-128g.pt, where is the llama.py here?