# University of Washington Math AI Lab: AI Model Publisher
Source: https://savrn.com/model-publishers/uw-math-ai
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

## Models

Model · Sentence similarity

### [MathLeap-Qwen-8B](https://savrn.com/models/mathleap-qwen-8b)

[University of Washington Math AI Lab](https://savrn.com/model-publishers/uw-math-ai)

A retrieval-tuned embedding model for mathematical text. Fine-tuned from on mathlib4 concepts via multi-view contrastive learning. On MELD — a benchmark of mathematical statements paired across radically different presentations (e.g., set-theoretic vs. category-theoretic phrasings of the same theorem) — MathLeap-Qwen-8B achieves MMR 0.43, beating its base Qwen3-Embedding-8B (0.32, +0.11) and the retrieval-specialized Octen-Embedding-8B (0.42). Each concept has up to four parallel representations: - nlinformal: informal natural-language description (all concepts) - nlinformal2: LLM-generated NL rephrasing (~85% of concepts) - leantype: Lean 4 type signature - leansignature: full Lean 4…

Open weights apache-2.0 7.6B parameters 40,960 tokens sentence-transformers

[View model](https://savrn.com/models/mathleap-qwen-8b)

## Explore More

- [All model publishers](https://savrn.com/model-publishers)
- [The model directory](https://savrn.com/models)
- [The dataset directory](https://savrn.com/datasets)

## Source

- Listed from their public repositories, read 2026-10-01.
- [Hugging Face profile](https://huggingface.co/uw-math-ai)
- [How the hub is built](https://savrn.com/model-hub/methodology)