view reply Thank you for the very nice blog. What are your thoughts on doing RL? Do you think the same results will be achieved?
3LM: Bridging Arabic, STEM, and Code through Benchmarking Paper • 2507.15850 • Published Jul 21, 2025 • 5
Running 81 Unlocking On-Policy Distillation for Any Model Family 📝 81 Improve model performance by transferring knowledge between different model families
Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale Paper • 2509.14008 • Published Sep 17, 2025 • 88
Running on Zero MCP Featured 311 NeuTTS-Air ☁ 311 Generate speech with your own voice using a reference audio sample
Sleeping 3 LFM2-1.2B Arabic RAG (AdaLoRA) 🚀 📊 3 Lightning-fast Arabic RAG | LFM2-1.2B finetuned with AdaLoRA
DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search Paper • 2509.25454 • Published Sep 29, 2025 • 146