Update README.md

README.md

@@ -22,6 +22,50 @@ Code: https://github.com/laihuiyuan/tacler
 Paper: https://arxiv.org/pdf/2601.21711
 
 
+## Quickstart
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "laihuiyuan/TACLer"
+
+# load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+
+# using Thinking or Nothinking mode
+think_mode = False
+
+question = "How many positive whole-number divisors does 196 have?"
+step_by_step = " Let's think step by step and output the final answer within \\boxed{}."
+messages = [
+    {"role": "user", "content": question + step_by_step}
+]
+prompt = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+if not think_mode:
+    prompt += 'Okay, I think I can solve it directly.\n</think>\n\n'
+model_inputs = tokenizer([prompt], return_tensors="pt").to(model.device)
+
+# conduct text completion
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=16384
+)
+output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
+output = tokenizer.decode(output_ids, skip_special_tokens=True).strip("\n")
+
+print("**PROMPT**\n", prompt)
+print("**OUTPUT**\n", output)
+
+```
+
 ## Citation
 ```
 @article{lai-etal-2026-tacler,