Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference Paper • 2412.13663 • Published 8 days ago • 103
view post Post 1013 remember boys and girls, always keep all your data, its never a waste of time! 👀 2 2 🧠 1 1 👍 1 1 + Reply
Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order Paper • 2404.00399 • Published Mar 30 • 41
view post Post Full fine-tuning of Microsoft's Phi2 on a single 4090 is now supported in axolotl. Thanks to @abacaj and @vikhyatk for their help with gradient checkpointing and flash attention fixes. alpaca finetune: openaccess-ai-collective/phi2-alpacawandb: https://wandb.ai/oaaic/phi2/runs/00pc4ugb?workspace=user-wing-lianmerged PR: https://github.com/OpenAccess-AI-Collective/axolotl/pull/1058 8 replies · 👍 15 15 ❤️ 8 8 + Reply
Generative Multimodal Models are In-Context Learners Paper • 2312.13286 • Published Dec 20, 2023 • 34