!pip install -q --upgrade torch

!pip install -q git+https://github.com/huggingface/transformers triton==3.4 git+https://github.com/triton-lang/triton.git@main#subdirectory=python/triton_kernels

!pip uninstall -q torchvision torchaudio -y

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "openai/gpt-oss-20b"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="cuda",
)

messages = [
    {"role": "system", "content": "Always respond in riddles"},
    {"role": "user", "content": "What is the weather like in Madrid?"},
]

inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt",
    return_dict=True,
).to(model.device)

generated = model.generate(**inputs, max_new_tokens=500)
print(tokenizer.decode(generated[0][inputs["input_ids"].shape[-1]:]))

messages = [
    {"role": "system", "content": "Always respond in riddles"},
    {"role": "user", "content": "Explain why the meaning of life is 42", "reasoning_effort": "high"},
]

inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt",
    return_dict=True,
).to(model.device)

generated = model.generate(**inputs, max_new_tokens=500)
print(tokenizer.decode(generated[0][inputs["input_ids"].shape[-1]:]))