diff --git a/README.md b/README.md index 478f9985b..65be1a687 100644 --- a/README.md +++ b/README.md @@ -145,7 +145,7 @@ python3 -m pip install torch numpy sentencepiece python3 convert-pth-to-ggml.py models/7B/ 1 # quantize the model to 4-bits -./quantize 7B +./quantize.sh 7B # run the inference ./main -m ./models/7B/ggml-model-q4_0.bin -t 8 -n 128