Update app.py

app.py

@@ -1,7 +1,8 @@
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 
-model_id = "daeguhighschool/my-student-chatbot-v2"  # 너의 모델 경로
+# SKT 한국어 GPT 모델
+model_id = "skt/ko-gpt-trinity-1.2B-v0.5"
 
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(model_id)
@@ -10,13 +11,18 @@ pipe = pipeline(
     "text-generation",
     model=model,
     tokenizer=tokenizer,
-    max_new_tokens=50,   # ← 이거 100보다 줄이면 반응 속도 확 줄어듦
+    max_new_tokens=100,
     do_sample=True,
-    temperature=0.7
+    temperature=0.7,
 )
 
 def chat(prompt):
-    result = pipe(prompt, max_new_tokens=100)[0]["generated_text"]
-    return result
+    response = pipe(prompt)[0]["generated_text"]
+    return response
 
-gr.Interface(fn=chat, inputs="text", outputs="text", title="학생용 LLM 챗봇").launch()
+gr.Interface(
+    fn=chat,
+    inputs="text",
+    outputs="text",
+    title="한국어 GPT 챗봇 (SKT Trinity 1.2B)"
+).launch()