README.md

metadata

license: cc
base_model:
  - Qwen/Qwen2.5-7B
  - Dexmal/Dexbotic-Base

Benchmark Results

Model	1	2	3	4	5	Average Length	Config
CogACT	83.8	72.9	64	55.9	48	3.246	-
DB-CogACT	93.5	86.7	80.3	76	69.8	4.063	playground/benchmarks/calvin/calvin_cogact.py