Hugging Face's logo

karantonis
/
bayesclue-checkpoints

Safetensors
uncertainty-quantification
bayesian
grpo
lora
Model card Files
xet
 Community
bayesclue-checkpoints / rl-matched-normal-step400 /tokenizer.json

Commit History

4B matched control (fixed-normal prior, identical SFT+RL recipe to hidden); folded LoRA, step 400
8c686c6
verified

karantonis commited on