update readme with example

README.md

@@ -14,18 +14,28 @@ licence: license
 
 # Model Card for tiny-starcoder-ft
 
-This model is a fine-tuned version of [bigcode/tiny_starcoder_py](https://huggingface.co/bigcode/tiny_starcoder_py).
+This model is a fine-tuned version of [bigcode/tiny_starcoder_py](https://huggingface.co/bigcode/tiny_starcoder_py) using a samples from [iamtarun/python_code_instructions_18k_alpaca](https://huggingface.co/datasets/iamtarun/python_code_instructions_18k_alpaca) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
 
 ```python
-from transformers import pipeline
+model_name = "sky-2002/tiny-starcoder-ft"
+model = AutoModelForCausalLM.from_pretrained(
+    pretrained_model_name_or_path=model_name
+).to(device)
+tokenizer = AutoTokenizer.from_pretrained(pretrained_model_name_or_path=model_name)
 
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="sky-2002/tiny-starcoder-ft", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
+prompt = "Write python code to calculate sum of a list"
+
+# Format with template
+messages = [{"role": "user", "content": prompt}]
+formatted_prompt = tokenizer.apply_chat_template(messages, tokenize=False)
+
+inputs = tokenizer(formatted_prompt, return_tensors="pt").to(device)
+
+outputs = model.generate(**inputs, max_new_tokens=100)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
 
 ## Training procedure