OzTianlu (Zixi "Oz" Li)

🚀 Introducing Asterisk — Hybrid ASPP-Attention Architecture! 🌟

NoesisLab/Asterisk

We’re excited to launch Asterisk, a cutting-edge language model by NoesisLab on Hugging Face! 🎉 Built on top of SmolLM2-135M-Instruct, Asterisk integrates Adjacency-Structured Parallel Propagation (ASPP) with standard attention to bring structured reasoning power into language modeling.

✨ Key Highlights:

🔹 Hybrid Architecture – Fuses graph-centric ASPP local reasoning with global attention for richer representations.
🔹 Enhanced Reasoning – ASPP enables iterative local state evolution that complements traditional transformer layers.
🔹 Efficient Design – ~171M parameters with smart supervised fine-tuning (Capybara dataset).
🔹 Flexible & Open – Apache-2.0 licensed and ready to integrate via Hugging Face 🤗 Transformers.

📈 Asterisk showcases how hybrid operators — inspired by theoretical frameworks like the Asterisk Operator — can bring structured reasoning into modern LMs in a scalable way.

👉 Try it out, explore the code, and start building: huggingface.co/NoesisLab/Asterisk

1 reply

·

upvoted a paper 1 day ago

Trainable Dynamic Mask Sparse Attention

Paper • 2508.02124 • Published Aug 4, 2025 • 18

liked a model 1 day ago

NoesisLab/Asterisk-Pi

Text Generation • 0.2B • Updated about 21 hours ago • 39 • 1

published a model 1 day ago

NoesisLab/Asterisk-Pi

Text Generation • 0.2B • Updated about 21 hours ago • 39 • 1

posted an update 2 days ago

Post

1018

🚀 Introducing Asterisk — Hybrid ASPP-Attention Architecture! 🌟

NoesisLab/Asterisk

We’re excited to launch Asterisk, a cutting-edge language model by NoesisLab on Hugging Face! 🎉 Built on top of SmolLM2-135M-Instruct, Asterisk integrates Adjacency-Structured Parallel Propagation (ASPP) with standard attention to bring structured reasoning power into language modeling.

✨ Key Highlights:

🔹 Hybrid Architecture – Fuses graph-centric ASPP local reasoning with global attention for richer representations.
🔹 Enhanced Reasoning – ASPP enables iterative local state evolution that complements traditional transformer layers.
🔹 Efficient Design – ~171M parameters with smart supervised fine-tuning (Capybara dataset).
🔹 Flexible & Open – Apache-2.0 licensed and ready to integrate via Hugging Face 🤗 Transformers.

📈 Asterisk showcases how hybrid operators — inspired by theoretical frameworks like the Asterisk Operator — can bring structured reasoning into modern LMs in a scalable way.

👉 Try it out, explore the code, and start building: huggingface.co/NoesisLab/Asterisk