From eaff11ca55d56aeec10ab4e88085113be71c4b61 Mon Sep 17 00:00:00 2001
From: hiepxanh <hiepxanh@gmail.com>
Date: Mon, 4 Mar 2024 21:12:50 -0800
Subject: [PATCH] readme: add convert-hf-to-gguf.py in example

I'm using huggingface model and find out that I need to use different script. So I make this change for people to save time instead of read or open new issue
---
 README.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/README.md b/README.md
index f754022de..3a23fe3f1 100644
--- a/README.md
+++ b/README.md
@@ -698,6 +698,9 @@ python convert.py models/mymodel/ --vocab-type bpe
 
 # update the gguf filetype to current version if older version is now unsupported
 ./quantize ./models/mymodel/ggml-model-Q4_K_M.gguf ./models/mymodel/ggml-model-Q4_K_M-v2.gguf COPY
+
+# convert the hunggingface model to ggml FP16 format
+python3 convert-hf-to-gguf.py models/mymodel/
 ```
 
 ### Run the quantized model