🚀 New breakthrough in TRL!
#1
by thinhpham8x - opened
Dưới đây là một phiên bản thảo luận tương tự, giữ vibe kỹ thuật – ngắn gọn, rõ ràng, phù hợp để đăng X:
⸻
🚀 New breakthrough in TRL!
Agent training with GRPO has officially landed 🔥
You can now train 🕵️♂️ tool-using agents that interact with external functions, APIs, and real-world workflows.
To help you get started fast:
📘 Notebook tutorial: https://github.com/huggingface/trl/blob/main/examples/notebooks/grpo_agent.ipynb
📂 Script examples: https://github.com/huggingface/trl/blob/main/examples/scripts/grpo_agent.py
📦 TRL v0.26.0 release: https://github.com/huggingface/trl/releases/tag/v0.26.0
The next generation of agent training is here. Let’s build. ⚡️