From 10dd53e5fb75ecc1e895328473d7800ad36c75f8 Mon Sep 17 00:00:00 2001
From: LYMDLUT <70597027+LYMDLUT@users.noreply.github.com>
Date: Thu, 18 Jan 2024 18:02:53 +0800
Subject: [PATCH] Update README_zh-CN.md

---
 README_zh-CN.md | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/README_zh-CN.md b/README_zh-CN.md
index 2125219..ac879ca 100644
--- a/README_zh-CN.md
+++ b/README_zh-CN.md
@@ -130,7 +130,12 @@ import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 tokenizer = AutoTokenizer.from_pretrained("internlm/internlm2-chat-7b", trust_remote_code=True)
 # 设置`torch_dtype=torch.float16`来将模型精度指定为torch.float16，否则可能会因为您的硬件原因造成显存不足的问题。
-model = AutoModelForCausalLM.from_pretrained("internlm/internlm2-chat-7b", trust_remote_code=True, torch_dtype=torch.float16).cuda()
+model = AutoModelForCausalLM.from_pretrained("internlm/internlm2-chat-7b", device_map="auto", trust_remote_code=True, torch_dtype=torch.float16)
+# (可选) 如果在低资源设备上，可以通过bitsandbytes加载4-bit或8-bit量化的模型，进一步节省GPU显存.
+  # 4-bit 量化的 InternLM 7B 大约会消耗 8GB 显存. 
+  # pip install -U bitsandbytes
+  # 8-bit: model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, load_in_8bit=True)
+  # 4-bit: model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, load_in_4bit=True)
 model = model.eval()
 response, history = model.chat(tokenizer, "你好", history=[])
 print(response)