Update app.py

app.py

@@ -9,7 +9,7 @@ from threading import Thread
 
 print(f"Starting to load the model to memory")
 m = AutoModelForCausalLM.from_pretrained(
-    "stabilityai/stablelm-2-zephyr-1_6b", torch_dtype=torch.float16, trust_remote_code=True)
+    "stabilityai/stablelm-2-zephyr-1_6b", torch_dtype=torch.float32, trust_remote_code=True)
 tok = AutoTokenizer.from_pretrained("stabilityai/stablelm-2-zephyr-1_6b", trust_remote_code=True)
 generator = pipeline('text-generation', model=m, tokenizer=tok)
 print(f"Sucessfully loaded the model to the memory")
@@ -23,14 +23,11 @@ def user(message, history):
 
 def chat(history):
     chat = []
-    print(history)
     for item in history:
         chat.append({"role": "user", "content": item[0]})
         if item[1] is not None:
             chat.append({"role": "assistant", "content": item[1]})
-    print(chat)
     messages = tok.apply_chat_template(chat, tokenize=False)
-    print(messages)
     # Tokenize the messages string
     model_inputs = tok([messages], return_tensors="pt")
     streamer = TextIteratorStreamer(
@@ -84,4 +81,4 @@ with gr.Blocks() as demo:
     clear.click(lambda: None, None, [chatbot], queue=False)
 
 demo.queue(max_size=32, concurrency_count=2)
-demo.launch()
+demo.launch()