#python#agent#agentic_ai#grpo#kimi_ai#llms#lora#qwen#qwen3#reinforcement_learning#rl
ART is a tool that helps you train smart agents for real-world tasks using reinforcement learning, especially with the GRPO method. The standout feature is RULER, which lets you skip the hard work of designing reward functions by using a large language model to automatically score how well your agent is doing—just describe your task, and RULER takes care of the rest. This makes building and improving agents much faster and easier, works for any task, and often performs as well as or better than hand-crafted rewards. You can install ART with a simple command and start training agents right away, even on your own computer or with cloud resources.
https://github.com/OpenPipe/ART
Пока весь мир ждет доступа к новой модели со зрением GPT-4V(ision), опенсорс команда (пара азитов со степенью PhD из американских вузов) уже выпустили свой аналог и бесплатную версию #LLaVA (Large Language and Vision Assistant), которая выдает результат (не) хуже GPT4V и может работать локально.
Вот такая скорость развития и конкуренции в этом новом #AI рынке.
🧠LLava - вебсайт
📄WhitePaper
🧬Github code
🔋Demo для потестить на своих дикпиках
🦒Colab (для запуска у себя на серваке)
#python#apple_silicon#florence2#idefics#llava#llm#local_ai#mlx#molmo#paligemma#pixtral#vision_framework#vision_language_model#vision_transformer
MLX-VLM lets you run, chat with, and fine-tune Vision Language Models (VLMs) plus audio/video models on your Mac using MLX—install easily with `pip install -U mlx-vlm`. Use CLI for quick text/image/audio generation (e.g., `mlx_vlm.generate --model ... --image photo.jpg`), Gradio UI for chats, Python scripts, or a FastAPI server with OpenAI-compatible endpoints supporting multi-images/videos. Features like TurboQuant cut KV cache memory by 76%, and LoRA/QLoRA fine-tuning works on consumer hardware. You benefit by experimenting with powerful multimodal AI locally—fast, memory-efficient, no cloud costs, perfect for Mac users tweaking models affordably.
https://github.com/Blaizzy/mlx-vlm