Update README.md

README.md

@@ -9,4 +9,24 @@ base_model:
 - HuggingFaceTB/SmolLM2-360M-Instruct
 pipeline_tag: text-generation
 ---
-v1: SFT -- 7658aab7702e56d9f5fa3b33bf7adcdae92f536b
+v1: SFT -- 7658aab7702e56d9f5fa3b33bf7adcdae92f536b
+
+
+```python
+
+rom transformers import AutoModelForCausalLM, AutoTokenizer
+checkpoint = "HuggingFaceTB/SmolLM2-360M-Instruct"
+
+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": "What is the capital of France."}]
+input_text=tokenizer.apply_chat_template(messages, tokenize=False)
+print(input_text)
+inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
+outputs = model.generate(inputs, max_new_tokens=50, temperature=0.2, top_p=0.9, do_sample=True)
+print(tokenizer.decode(outputs[0]))
+
+```