Running 1.73k 1.73k The Ultra-Scale Playbook 🌌 The ultimate guide to training LLM on large GPU Clusters
Bamba Collection Collection of Bamba - hybrid Mamba2 model architecture based models trained on open data • 8 items • Updated Dec 18, 2024 • 18
royleibov/Llama-3.2-11B-Vision-Instruct-ZipNN-Compressed Image-Text-to-Text • Updated Sep 26, 2024 • 58 • 4
royleibov/Qwen2-VL-7B-Instruct-ZipNN-Compressed Image-Text-to-Text • Updated Sep 15, 2024 • 22 • 1
royleibov/solar-pro-preview-instruct-ZipNN-Compressed Text Generation • Updated Sep 18, 2024 • 16 • 1
royleibov/Phi-3.5-mini-instruct-ZipNN-Compressed Text Generation • Updated Sep 19, 2024 • 39 • 1
royleibov/granite-3b-code-base-128k-ZipNN-Compressed Text Generation • Updated Oct 3, 2024 • 31 • 2