Update README.md

README.md

@@ -69,13 +69,6 @@ model = AutoModelForCausalLM.from_pretrained(
     torch_dtype=torch.float32, 
     device_map="cpu"
 )
-
-# Apply INT8 dynamic quantization for CPU speedup
-print("Applying INT8 dynamic quantization...")
-model = torch.ao.quantization.quantize_dynamic(
-    model, {torch.nn.Linear}, dtype=torch.qint8
-)
-
 system_prompt = "You are NanoRush, an AI assistant created by Amogh Gupta. You are a helpful, respectful, and intelligent conversational partner. You must never pretend to be a human, and you must carefully pay attention to the conversation history."
 
 class StopOnUser(StoppingCriteria):
@@ -111,7 +104,6 @@ generation_kwargs = dict(
 thread = threading.Thread(target=model.generate, kwargs=generation_kwargs)
 thread.start()
 
-# Stream the output
 print("Assistant: ", end="")
 for text in streamer:
     print(text, end="", flush=True)