{"repo":"Agora-Lab-AI/Atom","free":true,"listed":false,"github":"https://github.com/Agora-Lab-AI/Atom","clone":"git clone https://github.com/Agora-Lab-AI/Atom.git","description":"a suite of finetuned LLMs for atomically precise function calling 🧪","language":"Python","stars":16,"topics":["ai","artificial-intelligence","convolutional-neural-networks","function-calling","gpt-4","llama","llama2","llamacpp","ml","multi-modal"],"license":"MIT","category":"machine-learning","readme_excerpt":"Atom a suite of finetuned LLMs for atomically precise function calling 🧪 ✅ Massive function calling dataset of over 20M samples. ✅ First Model: Atom-Z-Tiny - Zephr trained on 100k samples ✅ Vision function calling coming soon Install You can install the package using pip Usage Training - To train the models, run accelerate config and enable DeepSpeed acceleration. deepspeed/zero3.json was the configuration file used for training.0 - Then run accelerate launch accelerate launch finetune.py We're finetuning this model on this dataset sh./run.sh - Dataset Citation","default_branch":null,"files":null,"tree":[],"storefront":"/r/Agora-Lab-AI","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/Agora-Lab-AI/Atom/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}