Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

randprior told RL final (step400) merged HF model

ckpt rl-randprior-told/global_step_325

ckpt rl-randprior-told/global_step_300

ckpt rl-randprior-told/global_step_275

ckpt rl-randprior-told/global_step_250

ckpt rl-randprior-told/global_step_225

ckpt rl-randprior-told/global_step_200

ckpt rl-randprior-told/global_step_175

ckpt rl-randprior-told/global_step_150

ckpt rl-randprior-told/global_step_125

ckpt rl-randprior-told/global_step_100

ckpt rl-randprior-told/global_step_75

ckpt rl-randprior-told/global_step_50

ckpt rl-randprior-hidden/global_step_25

ckpt rl-randprior-told/global_step_25

Upload folder using huggingface_hub

prior-fix SFT (randprior-told) step_3000 adapter

prior-fix SFT (randprior-hidden) step_3000 adapter

Stage-3 verbalization adapter v1 (LoRA r64, self-distil to frozen-I4 belief; KL(q||v)=0.021)

Upload README.md with huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

initial commit