test

app.py

@@ -59,6 +59,13 @@ def respond(
     #     add_generation_prompt = True, # Must add for generation
     #     return_tensors = "pt",
     # )
+    conversation = ''
+    for msg in messages:
+        if msg['role'] == 'user':
+            conversation += f"User: {msg['content']}\n"
+        elif msg['role'] == 'assistant':
+            conversation += f"Assistant: {msg['content']}\n"
+    conversation += "Assistant: "
     inputs = tokenizer.encode(messages, return_tensors='pt')
     # text_streamer = TextStreamer(tokenizer, skip_prompt = True)
     # for response in model.generate(input_ids = inputs, streamer = text_streamer, max_new_tokens = max_tokens, use_cache = True,