From a7d66b7342f8f6936feb4c61d7d90feeace98e15 Mon Sep 17 00:00:00 2001
From: Yuwen Hu <54161268+Oscilloscope98@users.noreply.github.com>
Date: Wed, 21 Jun 2023 10:04:34 +0800
Subject: [PATCH] [LLM] README revise for `llm_convert` (#8374)

* Small readme revise for llm_convert

* Small fix
---
 python/llm/README.md | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/python/llm/README.md b/python/llm/README.md
index 2910ba9e..1b3c0dc4 100644
--- a/python/llm/README.md
+++ b/python/llm/README.md
@@ -52,10 +52,9 @@ llm_convert(model="/path/to/llama-7b-hf/",
             model_format="pth",
             model_family="llama")
 # gptq model
-llm_convert(model="/path/to/vicuna-13B-1.1-GPTQ-4bit-128g.pt",
-            outfile="/path/to/out.bin",
+llm_convert(model="/path/to/vicuna-13B-1.1-GPTQ-4bit-128g/",
+            outfile="/path/to/vicuna-13B-int4/",
             model_format="gptq",
-            tokenizer_path="/path/to/tokenizer.model",
             model_family="llama")
 ```