codercat/AtmosRegime-Qwen3.5-9B-RL
Text Generation • 9B • Updated
AtmosRegime
Models from: Language models misapply atmospheric formulas until trained on a few worked examples
Note Reinforcement learning with verifiable rewards
codercat/AtmosRegime-Qwen3-8B-SFT-RL
Text Generation • 8B • UpdatedNote Fine-tuning on worked examples, then reinforcement learning
codercat/AtmosRegime-Qwen3-8B-Distill
Text Generation • 8B • UpdatedNote Distillation from a teacher given the correct formula