Add support for streaming output

cli_demo.py

@@ -7,18 +7,38 @@ model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).ha
 model = model.eval()
 
 os_name = platform.system()
+clear_command = 'cls' if os_name == 'Windows' else 'clear'
 
-history = []
-print("欢迎使用 ChatGLM-6B 模型，输入内容即可进行对话，clear 清空对话历史，stop 终止程序")
-while True:
-    query = input("\n用户：")
-    if query == "stop":
-        break
-    if query == "clear":
-        history = []
-        command = 'cls' if os_name == 'Windows' else 'clear'
-        os.system(command)
-        print("欢迎使用 ChatGLM-6B 模型，输入内容即可进行对话，clear 清空对话历史，stop 终止程序")
-        continue
-    response, history = model.chat(tokenizer, query, history=history)
-    print(f"ChatGLM-6B：{response}")
+
+def build_prompt(history):
+    prompt = "欢迎使用 ChatGLM-6B 模型，输入内容即可进行对话，clear 清空对话历史，stop 终止程序"
+    for query, response in history:
+        prompt += f"\n用户：{query}"
+        prompt += f"\nChatGLM-6B：{response}"
+    return prompt
+
+
+def main():
+    history = []
+    print("欢迎使用 ChatGLM-6B 模型，输入内容即可进行对话，clear 清空对话历史，stop 终止程序")
+    while True:
+        query = input("\n用户：")
+        if query == "stop":
+            break
+        if query == "clear":
+            history = []
+            os.system(clear_command)
+            print("欢迎使用 ChatGLM-6B 模型，输入内容即可进行对话，clear 清空对话历史，stop 终止程序")
+            continue
+        count = 0
+        for response, history in model.stream_chat(tokenizer, query, history=history):
+            count += 1
+            if count % 8 == 0:
+                os.system(clear_command)
+                print(build_prompt(history), flush=True)
+        os.system(clear_command)
+        print(build_prompt(history), flush=True)
+
+
+if __name__ == "__main__":
+    main()

web_demo.py

@@ -12,15 +12,15 @@ MAX_BOXES = MAX_TURNS * 2
 def predict(input, max_length, top_p, temperature, history=None):
     if history is None:
         history = []
-    response, history = model.chat(tokenizer, input, history, max_length=max_length, top_p=top_p,
-                                   temperature=temperature)
-    updates = []
-    for query, response in history:
-        updates.append(gr.update(visible=True, value="用户：" + query))
-        updates.append(gr.update(visible=True, value="ChatGLM-6B：" + response))
-    if len(updates) < MAX_BOXES:
-        updates = updates + [gr.Textbox.update(visible=False)] * (MAX_BOXES - len(updates))
-    return [history] + updates
+    for response, history in model.stream_chat(tokenizer, input, history, max_length=max_length, top_p=top_p,
+                                               temperature=temperature):
+        updates = []
+        for query, response in history:
+            updates.append(gr.update(visible=True, value="用户：" + query))
+            updates.append(gr.update(visible=True, value="ChatGLM-6B：" + response))
+        if len(updates) < MAX_BOXES:
+            updates = updates + [gr.Textbox.update(visible=False)] * (MAX_BOXES - len(updates))
+        yield [history] + updates
 
 
 with gr.Blocks() as demo: