array
/

Qwen2.5-VL-SAT

text-generation-inference

Model card Files Files and versions

array commited on 27 days ago

Commit

184fdb0

·

verified ·

1 Parent(s): b5bb67c

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -12,7 +12,7 @@ base_model:
 A strong spatial Qwen 2.5 VL baseline.
-Post-trained on SAT, and just the answers from Video-R1. The exact mix is 40% SAT, 20% Zebra-COT, 20% Video-R1.
 ## Get Started

 A strong spatial Qwen 2.5 VL baseline.
+Post-trained on SAT, and just the answers from Video-R1. The exact mix is 60% SAT, 40% Video-R1.
 ## Get Started