Update app.py

app.py

@@ -1,25 +1,8 @@
-import openai
 import gradio as gr
 
-openai.api_key = "sk-R3HlMsYBk0NpAlLu2aA4B19054Ea4884A2Cf93D25662243d"
-openai.api_base="https://apai.zyai.online/v1"
-
-def predict(message, history):
-    history_openai_format = []
-    for human, assistant in history:
-        history_openai_format.append({"role": "user", "content": human })
-        history_openai_format.append({"role": "assistant", "content":assistant})
-    history_openai_format.append({"role": "user", "content": message})
-
-    response = openai.ChatCompletion.create(
-        model="gpt-3.5-turbo",  # 对话模型的名称
-        messages=history_openai_format,
-        temperature=1,  # 值在[0,1]之间，越大表示回复越具有不确定性
-        max_tokens=600,  # 回复最大的字符数
-        top_p=1,
-        frequency_penalty=0,  # [-2,2]之间，该值越大则更倾向于产生不同的内容
-        presence_penalty=0,  # [-2,2]之间，该值越大则更倾向于产生不同的内容
-    )
-    yield response.choices[0]['message']['content']
-
-gr.ChatInterface(predict).queue().launch()
+from transformers import AutoTokenizer, AutoModel
+tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm3-6b", trust_remote_code=True)
+model = AutoModel.from_pretrained("THUDM/chatglm3-6b", trust_remote_code=True).half().cuda()
+model = model.eval()
+response, history = model.chat(tokenizer, "你好", history=[])
+print(response)