Add Transformers Python example to Usage

README.md

@@ -145,6 +145,40 @@ MMLU-Pro, SuperGPQA and HLE (text-only) sets.
 
 Quark runs anywhere Qwen3.5-9B does (Transformers, vLLM, SGLang). We recommend an output budget of 131,072 tokens for best performance.
 
+With [Transformers](https://github.com/huggingface/transformers) (`pip install -U transformers accelerate`; the bf16
+weights need about 20 GB of GPU memory):
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "FirstPrinciplesLabs/quark"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, dtype="auto", device_map="auto")
+
+messages = [{"role": "user", "content": (
+    "A particle is in the ground state of a 1D infinite square well of width L. The well suddenly expands to "
+    "width 2L. What is the probability of finding the particle in the ground state of the new well?"
+)}]
+inputs = tokenizer.apply_chat_template(
+    messages, add_generation_prompt=True, enable_thinking=True, return_tensors="pt", return_dict=True
+).to(model.device)
+
+output = model.generate(
+    **inputs,
+    max_new_tokens=32768,  # hard problems can need up to 131,072
+    do_sample=True, temperature=1.0, top_p=0.95, top_k=20,
+)
+text = tokenizer.decode(output[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
+
+thinking, finished, answer = text.partition("</think>")
+if not finished:
+    print("Stopped while still thinking; raise max_new_tokens.")
+print(answer.strip())  # expected: 32 / (9 pi^2), about 0.36
+```
+
+Transformers' `generate` has no presence penalty, so for long answers and for serving, we recommend vLLM, which
+supports the full recommended sampling settings:
+
 ```bash
 vllm serve FirstPrinciplesLabs/quark \
   --max-model-len 135168 --reasoning-parser qwen3