Update README_CN.md

README_CN.md

@@ -82,6 +82,11 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 from transformers.generation import GenerationConfig
 
 tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True)
+## 使用bf16精度
+# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True, bf16=True).eval()
+## 使用fp16精度
+# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True, fp16=True).eval()
+# 默认使用fp32精度
 model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True).eval()
 model.generation_config = GenerationConfig.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True) # 可指定不同的生成长度、top_p等相关超参
 
@@ -115,6 +120,11 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 from transformers.generation import GenerationConfig
 
 tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-7B", trust_remote_code=True)
+## 使用bf16精度
+# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B", device_map="auto", trust_remote_code=True, bf16=True).eval()
+## 使用fp16精度
+# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B", device_map="auto", trust_remote_code=True, fp16=True).eval()
+# 默认使用fp32精度
 model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B", device_map="auto", trust_remote_code=True).eval()
 model.generation_config = GenerationConfig.from_pretrained("Qwen/Qwen-7B", trust_remote_code=True) # 可指定不同的生成长度、top_p等相关超参