Update README.md

README.md

@@ -12,7 +12,7 @@ tags:
 # OmniMouse-80M
 
 Pretrained OmniMouse: a multi-modal, multi-task transformer for the mouse visual cortex.
-Trained on 3.1M neurons from 73 mice across 323 sessions (150B+ neural tokens),
+Trained on 2.3M neurons from 73 mice across 323 sessions (150B+ neural tokens),
 unified across neural prediction, behavioral decoding, and neural forecasting.
 
 ![Overview](fig1_overview.png)
@@ -20,7 +20,7 @@ unified across neural prediction, behavioral decoding, and neural forecasting.
 ## Abstract
 
 Scaling data and models has transformed AI. Does the same hold for brain modeling?
-We train multi-modal, multi-task models on 3.1 million neurons from 73 mice (150B+
+We train multi-modal, multi-task models on 2.3 million neurons from 73 mice (150B+
 neural tokens), flexibly supporting neural prediction, behavioral decoding, and neural
 forecasting. OmniMouse achieves state-of-the-art performance, outperforming specialized
 baselines across virtually all regimes. Yet performance scales with more data while
@@ -82,7 +82,7 @@ representation.
 
 ## Training data
 
-3M+ single neurons from the visual cortex of 73 mice across 323 sessions, totaling
+2.3M+ single neurons from the visual cortex of 73 mice across 323 sessions, totaling
 150B+ neural tokens. Mice viewed naturalistic movies (cinematic clips, Sports-1M),
 ImageNet images, and parametric stimuli (Gabors, random dot kinematograms, pink noise,
 model-generated stimuli) while running on a wheel. Pupil position, pupil dilation and