Update README.md

README.md

@@ -64,8 +64,16 @@ You can run the smashed model with these steps:
       
       tokenizer = AutoTokenizer.from_pretrained("PrunaAI/Mixtral-8x22B-v0.1-bnb-4bit-smashed")
       model = AutoModelForCausalLM.from_pretrained(
-        "PrunaAI/Mixtral-8x22B-v0.1-bnb-4bit-smashed",
+      "PrunaAI/Mixtral-8x22B-v0.1-bnb-4bit-smashed",
+      device_map="sequential", 
+      torch_dtype=torch.bfloat16,
       )
+      
+      text = "Who is Einstein?"
+      inputs = tokenizer(text, return_tensors="pt")
+      
+      outputs = model.generate(**inputs, max_new_tokens=20)
+      print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 
     ```