fix readme

README.md

@@ -45,7 +45,10 @@ GLM-4-9B 是智谱 AI 推出的最新一代预训练模型 GLM-4 系列中的开
 
 ```python
 import torch
-from Transformers
+from transformers import (
+    AutoModelForCausalLM,
+    AutoTokenizer,
+)
 
 device = "cuda"
 
@@ -62,7 +65,7 @@ inputs = tokenizer.apply_chat_template([{"role": "user", "content": query}],
 
 inputs = inputs.to(device)
 model = AutoModelForCausalLM.from_pretrained(
-    "ZhipuAI/glm-4-9b-chat-1m",
+    "THUDM/glm-4-9b-chat-1m",
     torch_dtype=torch.bfloat16,
     low_cpu_mem_usage=True,
     trust_remote_code=True

README_en.md

@@ -38,13 +38,16 @@ Use the transformers backend for inference:
 
 ```python
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import (
+    AutoModelForCausalLM,
+    AutoTokenizer,
+)
 
 device = "cuda"
 
 tokenizer = AutoTokenizer.from_pretrained("THUDM/glm-4-9b-chat-1m",trust_remote_code=True)
 
-query = "hello"
+query = "你好"
 
 inputs = tokenizer.apply_chat_template([{"role": "user", "content": query}],
                                        add_generation_prompt=True,