Update README.md

README.md

@@ -59,15 +59,16 @@ model_id = "RetentionLabs/TTT-Linear-1.3B-Base-Books-32k"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
-    torch_dtype=torch.bfloat16,
     trust_remote_code=True,
+    dtype=torch.bfloat16,
     device_map="auto"
 )
 
 # Generate
-inputs = tokenizer("The future of AI is", return_tensors="pt").to(model.device)
-outputs = model.generate(**inputs, max_new_tokens=100)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+with torch.autocast(device_type="cuda", dtype=torch.bfloat16):
+    inputs = tokenizer("The future of AI is", return_tensors="pt").to(model.device)
+    outputs = model.generate(**inputs, max_new_tokens=100)
+    print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
 
 ### From scratch