Merge 81c9c9e8a6 into 1808ee0500

README.md

@@ -142,7 +142,7 @@ ls ./models
 python3 -m pip install torch numpy sentencepiece
 
 # convert the 7B model to ggml FP16 format
-python3 convert-pth-to-ggml.py models/7B/ 1
+./convert-pth-to-ggml.py models/7B/ 1
 
 # quantize the model to 4-bits
 ./quantize ./models/7B/ggml-model-f16.bin ./models/7B/ggml-model-q4_0.bin 2

convert-pth-to-ggml.py

@@ -1,3 +1,5 @@
+#!/usr/bin/env python
+
 # Convert a LLaMA model checkpoint to a ggml compatible file
 #
 # Load the model using Torch