Adding code for generating model outputs

README.md

@@ -34,15 +34,19 @@ This repository contains weights for RefuelLLM-2-small that are compatible for u
 See the snippet below for usage with Transformers:
 
 ```python
->>> import transformers
 >>> import torch
+>>> from transformers import AutoModelForCausalLM, AutoTokenizer
 
 >>> model_id = "refuelai/Llama-3-Refueled"
+>>> tokenizer = AutoTokenizer.from_pretrained(model_id)
+>>> model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
 
->>> pipeline = transformers.pipeline(
-    "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto"
-)
->>> pipeline("Hey how are you doing today?")
+>>> messages = [{"role": "user", "content": "Is this comment toxic or non-toxic: RefuelLLM is the new way to label text data!"}]
+
+>>> inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to("cuda")
+
+>>> outputs = model.generate(inputs, max_new_tokens=20)
+>>> print(tokenizer.decode(outputs[0]))
 ```
 
 ## Training Data