Update README.md

README.md

@@ -71,7 +71,7 @@ tokens = tokenizer.encode_plus(text)['input_ids']
 tokens = torch.tensor(tokens)[None,].to(device)
 
 with torch.no_grad():
-        out = llama.generate(tokens, do_sample=False, max_length=128, eos_token_id=tokenizer.eos_token_id)[0]
+        out = model.generate(tokens, do_sample=False, max_length=128, eos_token_id=tokenizer.eos_token_id)[0]
         out = tokenizer.decode(out.cpu().numpy().tolist())
         print(out)
 ```