Year | Work | Authors | Links |
---|---|---|---|
2025 | Towards Fully FP8 GEMM LLM Training at Scale | A. Hernandez-Cano*, D. Garbaya*, I. Schalg, M. Jaggi | 📄 Preprint | 💻 Code |
2024 | Falcon3 family of open models 🦅 | Falcon-LLM Team | 📄 Report (soon) | 📜 Blog | 🤗 Collection | 💬 Demo |