🔥 Trending Repository: ART

📝 Description: Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!

🔗 Repository URL: https://github.com/OpenPipe/ART

🌐 Website: https://art.openpipe.ai

📖 Readme: https://github.com/OpenPipe/ART#readme

📊 Statistics:
🌟 Stars: 6K stars
👀 Watchers: 35
🍴 Forks: 380 forks

💻 Programming Languages: Python - Jupyter Notebook - Shell

🏷️ Related Topics:

#agent #reinforcement_learning #rl #lora #llms #qwen #kimi_ai #agentic_ai #grpo #qwen3

==================================
🧠 By: https://yangx.top/DataScienceM

🔥 Trending Repository: transformerlab-app

📝 Description: Open Source Application for Advanced LLM + Diffusion Engineering: interact, train, fine-tune, and evaluate large language models on your own computer.

🔗 Repository URL: https://github.com/transformerlab/transformerlab-app

🌐 Website: https://transformerlab.ai/

📖 Readme: https://github.com/transformerlab/transformerlab-app#readme

📊 Statistics:
🌟 Stars: 3.9K stars
👀 Watchers: 31
🍴 Forks: 363 forks

💻 Programming Languages: TypeScript - JavaScript

🏷️ Related Topics:

#electron #transformers #llama #lora #diffusion #mlx #diffusion_models #llms #stability_diffusion #rlhf

==================================
🧠 By: https://yangx.top/DataScienceM