Update README.md

README.md

@@ -29,6 +29,28 @@ To build SmolLM-Instruct, we instruction tuned the models using publicly availab
 
 This is the SmolLM-360M-Instruct.
 
+### Generation
+```bash
+pip install transformers
+```
+
+```python
+# pip install transformers
+from transformers import AutoModelForCausalLM, AutoTokenizer
+checkpoint = "HuggingFaceTB/SmolLM-360M-Instructt"
+
+device = "cuda" # for GPU usage or "cpu" for CPU usage
+tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+# for multiple GPUs install accelerate and do `model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map="auto")`
+model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
+
+messages = [{"role": "user", "content": "List the steps to bake a chocolate cake from scratch."}]
+input_text=tokenizer.apply_chat_template(messages, tokenize=False)
+print(input_text)
+inputs = tokenizer.encode(input_text, return_tensors="pt").to("cuda")
+outputs = model.generate(inputs, max_new_tokens=100, temperature=0.6, top_p=0.92, do_sample=True)
+print(tokenizer.decode(outputs[0]))
+```
 
 # Limitations