Instructions to use mystery-1057/DRAM-PI05-RMBench with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use mystery-1057/DRAM-PI05-RMBench with LeRobot:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Download README.md from mystery-1057/DRAM-PI05-RMBench: direct link, hf CLI and curl.
- Browser
- Download file 1.4 kB
-
https://huggingface.co/mystery-1057/DRAM-PI05-RMBench/resolve/main/README.md
- Command line
-
hf download hf://mystery-1057/DRAM-PI05-RMBench/README.md
-
curl -L -o README.md https://huggingface.co/mystery-1057/DRAM-PI05-RMBench/resolve/main/README.md
tags:
- robotics
- lerobot
- dram
- rmbench
DRAM-PI05-RMBench
This repository contains the 50,000-step RMBench checkpoint for LeRobot π₀.₅ with DRAM streaming memory. It uses the native_kv mode, which takes keys and values from the vision-language model as inputs to the memory bank.
Download
hf download mystery-1057/DRAM-PI05-RMBench \
--local-dir ./checkpoints/dram-pi05-rmbench
Keep the checkpoint directory together. The policy loads the model, tokenizer, and observation and action processors from this directory.
Evaluate on RMBench
From the root of the DRAM-enabled LeRobot v0.6.0 checkout, with the PI dependencies installed, start the policy server:
python scripts/eval_recurrent_pi05_with_rmbench.py \
--policy.path=./checkpoints/dram-pi05-rmbench \
--policy.device=cuda:0 \
--policy.dtype=float32 \
--policy.use_amp=false \
--policy.compile_model=false \
--policy.gradient_checkpointing=false \
--strict_weights=true \
--memory_tick=stride \
--observation_stride=5 \
--n_action_steps=5 \
--server.host=127.0.0.1 \
--server.port=19000
Run the RMBench XPolicyLab client separately and connect to 127.0.0.1:19000. The evaluation uses demo_clean, seen instructions, and 50 Hz control. The server updates DRAM memory once every five control steps and resets memory at the start of each episode.