Energy-Based Transformers are Scalable Learners and Thinkers Paper • 2507.02092 • Published Jul 2, 2025 • 71
view article Article Hugging Face and Cerebras bring Gemma 4 to real-time voice AI +2 A-Mahla, andito, lvwerra, vyassaurabh • 22 days ago • 83
view article Article Investing in Performance: Fine-tune small models with LLM insights - a CFM case study +5 oahouzi, florentgbelidji, sylvainc, jlhour, Pirash, bpatault, MGoibert • Dec 3, 2024 • 40
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference Paper • 2412.13663 • Published Dec 18, 2024 • 168
view article Article ModernBERTic: The First Modern Encoder for South Slavic Languages permitt • Apr 30 • 2