Update README.md

README.md

@@ -45,18 +45,18 @@ model = PeftModel.from_pretrained(model, "damerajee/Tinyllama-sft-small")l")
 inputs = tokenizer(
 [
     alpaca_prompt.format(
-        "i want to learn machine learning help me", 
+        "choose ronaldo or messi?", # instruction
         "", # input
         "", # output
     )
-]*1, return_tensors = "pt").to("cuda")
+]*1, return_tensors = "pt")
 
-outputs = model.generate(**inputs, max_new_tokens = 312, use_cache = True)
+outputs = model.generate(**inputs, max_new_tokens = 128, use_cache = True)
 tokenizer.batch_decode(outputs)
 ```
 
 # Model Information
-The base model [unsloth/tinyllama-bnb-4bit](https://huggingface.co/unsloth/tinyllama-bnb-4bit)was Instruct finetuned using [Unsloth](https://github.com/unslothai/unsloth)
+The base model [unsloth/tinyllama-bnb-4bit](https://huggingface.co/unsloth/tinyllama-bnb-4bit) was Instruct finetuned using [Unsloth](https://github.com/unslothai/unsloth)
 
 # Training Details