#jupyter_notebook#chinese_llm#chinese_nlp#finetune#generative_ai#instruct_gpt#instruction_set#llama#llm#lora#open_models#open_source#open_source_models#qlora
AirLLM is a tool that lets you run very large AI models on computers with limited memory by using a smart layer-by-layer loading technique instead of traditional compression methods. You can run a 70-billion-parameter model on just 4GB of GPU memory, or even a 405-billion-parameter model on 8GB, without losing model quality. The benefit is that you can use powerful AI models on affordable hardware without expensive upgrades, and the tool also offers optional compression features that can speed up performance by up to 3 times while maintaining accuracy.
https://github.com/lyogavin/airllm
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