trjxter author hub

Gwimi 4 12B IT GGUF Quantized GGUF releases of Gwimi 4 12B IT , a Gemma 4 12B instruction model post trained through: 1. Supervised Fine Tuning SFT on a 20,000 example reasoning mixture. 2. Group Sequence Policy Optimization GSPO on 12,000 frozen reinforcement learning prompts. …