Preview - rendered architecture diagrams; full validated atlas + dataset coming.
TorchLens Menagerie
Models
Dataset
About
Theme
Back to models
qwen2_audio_encoder:base-audio-encoder
audio_speech
qwen2 audio
validation pending
Architecture diagram
Rendered with TorchLens / Graphviz
+
-
Fit
Open SVG
Unrolled - full
