Views
No views yet
TeleEmbodied/PRTS-4B. This is the exact checkpoint used to report the LIBERO numbers in the PRTS paper. For the base model card (architecture, prompt format, contrastive RL design), please refer to the parent PRTS-4B repository.TeleEmbodied/PRTS-4B with the launch script scripts/ft/launch_finetune.sh in the open-source repo. Key settings:| Base model | TeleEmbodied/PRTS-4B |
| Dataset config | configs/post-train/libero.yaml |
| Embodiment tag | libero_panda |
| Hardware | 4 GPUs, DeepSpeed ZeRO-2, bf16, flash_attention_3, no gradient checkpointing |
| Steps | 30,000 total, 5,000 warmup, save every 10,000 |
| Effective batch | 8 (per-device) × 4 GPUs × 1 (grad-acc) = 32 |
| LRs | 1e-5 for vision / merger / LLM; 1e-4 for the action head |
| Scheduler | cosine_with_min_lr (min 1e-6) |
| Optimizer | AdamW (β1=0.9, β2=0.95, ε=1e-8), weight decay 1e-8, grad clip 1.0 |
| Action head | DiT-L + MoT action expert, chunk size 20, max action dim 32 |
| Action normalization | QUANTILE (stats bundled in this checkpoint) |
| Seed | 42 |
scripts/serve_policy.py. Update the EnvMode.LIBERO entry in DEFAULT_CHECKPOINT so that dir= points to your local download of this repo. Normalization stats are already bundled in the checkpoint, so dataset_path can be left as None:1EnvMode.LIBERO: Checkpoint(
2 config="prts_libero",
3 dir="/path/to/PRTS-4B-libero", # local download path of this repo
4 action_dim=7,
5 dataset_path=None, # normalization stats are bundled in the checkpoint
6 state_mode="QUANTILE",
7),examples/libero/README.md, then start the policy server from the PRTS repo root with examples/libero/run_libero_server.sh:1bash examples/libero/run_libero_server.sh
2# which runs:
3# CUDA_VISIBLE_DEVICES=0 python scripts/serve_policy.py --env LIBERO --port 100001@article{zhang2026prts,
2 title = {PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations},
3 author = {Yang Zhang and Jiangyuan Zhao and Chenyou Fan and Fangzheng Yan and Tian Li and Haitong Tang and Sen Fu and Xuan'er Wu and Qizhen Weng and Weinan Zhang and Xiu Li and Chi Zhang and Chenjia Bai and Xuelong Li},
4 journal = {arXiv preprint arXiv:2604.27472},
5 year = {2026},
6}