import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("ChengYangYang/bpp-reading-pointer-weights", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Decoupled reading: model weights (backup 2026-09-30)
reader_weights/: decoupled reader (12obs_encoder.ptr_*tensors) + normalizer + cfg for every sequence-training run (INDEX.json); the BPP policy is frozen, so released BPP checkpoint + these = full model.full/: full checkpoints, learned-count reader (LEVT L1/L2) and joint-training ablations.full_policy_trained/: runs that also trained the policy (sync/content/nocopy/lnc/dag/factorslot).pi05_lora/: pi0.5 LoRA on LIBERO-Gen goal chains (openpi), steps 5k-50k; evaluated: 10000, 20000, 49999.baselines/: RoboSSM (20,596 steps) and UniSkill (epoch 500) retrained on LIBERO-Gen Chain.earlier_lines/: models from earlier project lines (subgoal/goal image, demo generators, keyframe, pose, trajectory, anchor, phase, boundary reader).
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support