Downloads · 30 days
0
lair-nyu/yor_icl_pi0_fast_easy_pnp_v2_sanity15k_annealing
yor_icl_pi0_fast_easy_pnp_v2_sanity15k_annealing is a machine learning model from lair-nyu. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
pi0-FAST sanity check (4-task pnp subset, 15k steps, correctly-scaled cosine decay, batch 128, 2xH200)
Downloads · 30 days
0
Access
Public
Updated Aug 30, 2026
Repo size
10.8 GB
Likes
0
Public
Click a slice to open those files.
Other10.8 GB · 100%
From the Hugging Face model README
pi0-FAST sanity check (4-task pnp subset, 15k steps, correctly-scaled cosine decay, batch 128, 2xH200)
yor_icl_pi0_fast_easy_pnp_v2_sanity15k_annealingparams/ (deployable policy weights) + assets/ (norm stats etc.) only -- train_state/ (optimizer state, needed only to resume this exact training run) is NOT included.FAST-tokenized analogue of yor_icl_pi05_easy_pnp_v2, run on the same small 4-task subset to validate the FAST backend/data pipeline ahead of the expanded pi0-FAST run (yor_icl_pi0_fast_expanded). decay_steps matched to num_train_steps (same annealing fix as sanity15k_annealing).