Bariona/fact-wam

FACT — RoboTwin Checkpoint

Action-transformer checkpoint for FACT (Failure-Aware Causal Training for World-Action Models), fine-tuned from Wan2.2-TI2V-5B on the RoboTwin 2.0 benchmark (failure co-training, 250k steps).

Usage

The repo ships the matching normalization stats (norm_stats_delta.json), so inference/eval needs no dataset download or training:

huggingface-cli download Bariona/fact-wam --local-dir ./models/fact-wam

python -m scripts.inference_server \
  --model_id ./models/Wan2.2-TI2V-5B-Diffusers \
  --transformer_path ./models/fact-wam/transformer \
  --stats_path ./models/fact-wam/norm_stats_delta.json \
  --port 8093

For closed-loop RoboTwin evaluation, set TRANSFORMER_PATH=./models/fact-wam/transformer and STATS_PATH=./models/fact-wam/norm_stats_delta.json in evaluation/robotwin/launch_config.yml.