Create README.md

README.md

@@ -0,0 +1,46 @@
+# Quickstart
+
+## Environment
+```
+pip install vllm # vllm>=v0.8.5.post1 should work
+pip install transformers # transformers>=4.52.4 should work
+```
+
+
+## Using vLLM to generate
+```python
+from vllm import LLM, SamplingParams
+from transformers import AutoTokenizer
+
+
+def convert_question_to_messages(question: str):
+    messages = [
+        {"role": "user",
+         "content": question + " Let's think step by step and output the final answer within \\boxed{}."}
+    ]
+    return messages
+
+
+model_id="ethan1115/DeepSearch-1.5B"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+sampling_params = SamplingParams(
+    temperature=0.6, 
+    top_p=0.95, 
+    max_tokens=32768
+)
+
+model = LLM(
+    model=model_id,
+    tensor_parallel_size=1
+)
+prompt = tokenizer.apply_chat_template(
+    convert_question_to_messages("Find the sum of all integer bases $b>9$ for which $17_{b}$ is a divisor of $97_{b}$."), 
+    add_generation_prompt=True, 
+    tokenize=False
+)
+
+outputs = model.generate({"prompt": prompt}, sampling_params=sampling_params, use_tqdm=False)
+response = outputs[0].outputs[0].text
+print(response)
+```