Hugging Face's logo

Maorb23
/
qwen35-2b-early-exit-adapters

Model card Files
xet
 Community

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Qwen3.5-2B Early Exit Adapters

Adapters trained to map intermediate hidden states to final-model-like next-token distributions.

Base model: Qwen/Qwen3.5-2B
Layers: [4, 8, 12, 16, 18, 20]
Sequence length: 128
Training steps: 500
Loss: KL distillation to final logits

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support