π In a Training Loop
Maxence Lasbordes
AI & ML interests
Large Language Models, Post-Training, Reinforcement Learning
Recent Activity
published a model about 19 hours ago
lightonai/SASS-Qwen3-1.7B-Weighted-SFT-ColGREP published a model about 19 hours ago
lightonai/SASS-Qwen3-1.7B-RL-FileF1-TurnPenalty-GREP published a model about 19 hours ago
lightonai/SASS-MiniCPM5-1B-Weighted-SFT-GREP