app.py

@@ -61,16 +61,18 @@ if model_cache_path:
     model_size_gb = Path(model_cache_path[0]).stat().st_size / 2**30
     logger.info(f"{model_name=} {model_size_gb=:.2f} GB")
 
-# with gr.Blocks() as demo:
-#     chatbot = gr.Chatbot()
-#     msg = gr.Textbox()
-#     clear = gr.ClearButton([msg, chatbot])
 
-#     def respond(message, chat_history):
-#         response, chat_history = model.chat(tokenizer, message, history=chat_history, temperature=0.7, repetition_penalty=1.2, max_length=128)
-#         chat_history.append((message, response))
-#         return "", chat_history
+def respond(message, chat_history):
+    response, chat_history = model.chat(tokenizer, message, history=chat_history, temperature=0.7, repetition_penalty=1.2, max_length=128)
+    chat_history.append((message, response))
+    return "", chat_history
 
-#     msg.submit(respond, [msg, chatbot], [msg, chatbot])
 
-# demo.launch()
+with gr.Blocks() as block:
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox()
+
+clear = gr.ClearButton([msg, chatbot])
+msg.submit(respond, [msg, chatbot], [msg, chatbot])
+
+block.queue().launch()

requirements.txt

@@ -2,6 +2,7 @@ torch
 transformers
 sentencepiece
 cpm_kernels
-accelerate
+# accelerate
+# bitsandbytes
 
 loguru