DeepSeek 강화학습 라이브러리 나왔네요.

# https://huggingface.co/docs/trl/main/en/grpo_trainer
# https://velog.io/@d4r6j/DeepSeek-R1-paper-review

# pip install trl

from datasets import load_dataset
from trl import GRPOConfig, GRPOTrainer

dataset = load_dataset("trl-lib/tldr", split="train")

# Define the reward function, which rewards completions that are close to 20 characters
def reward_len(completions, **kwargs):
    return [-abs(20 - len(completion)) for completion in completions]

training_args = GRPOConfig(output_dir="Qwen2-0.5B-GRPO", logging_steps=10)
trainer = GRPOTrainer(
    model="Qwen/Qwen2-0.5B-Instruct",
    reward_funcs=reward_len,
    args=training_args,
    train_dataset=dataset,
)
trainer.train()

훔…