Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
FLUX2-TE-Trimmed7L-Research – AI Model by WaveCut | AlphaNeural AI
You can deploy this model and start earning money today!
WaveCut
/
FLUX2-TE-Trimmed7L-Research
like
0
safetensors
mistral3
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
FLUX2-TE-Trimmed7L-Research
WARNING: Experimental research artifact. Do NOT use in production.
What this is
Model name: FLUX2-TE-Trimmed7L-Research
Text transformer depth: 7 layers
Vision tower depth: 24 layers (unchanged)
Caveats
Intended for experimentation and further distillation, not end-user deployment.
Rotary and patch positional inv_freq buffers are created at load time (not stored).
How it was built
Shrank teacher text path to 7 layers (evenly spaced) while keeping vision depth intact.
Stream-copied only needed tensors; other text layers were pruned.
