VibeThinker-3B and the Strength of Post-Training (opens in new tab)
Short note on VibeThinker-3B, a 3B model based on Qwen2.5-Coder-3B whose reported coding and reasoning results point to strong post-training.
Read the original articleShort note on VibeThinker-3B, a 3B model based on Qwen2.5-Coder-3B whose reported coding and reasoning results point to strong post-training.
Read the original article