# Jackson Davis: Open-Weight Models and Datasets
Source: https://savrn.com/model-publishers/handwoven8588
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

## Models

Model

### [CodeRankEmbed-flash-attn](https://savrn.com/models/coderankembed-flash-attn)

[Jackson Davis](https://savrn.com/model-publishers/handwoven8588)

A bf16 quantization of nomic-ai/CodeRankEmbed with a three-tier attention dispatch built into a custom modelinghfnomicbert.py shipped in this repo. It is not a finetune — the weights are the original CodeRankEmbed weights cast to bf16 (no further training). Two of the three tiers replace the original eager O(seq²) attention with an O(N) unpadded path; the third keeps the original eager algorithm as the correctness reference and universal fallback. nomic-ai/CodeRankEmbed loads through trustremotecode, and its attention path is eager only — activation memory grows as batch × heads × seq², which OOMs at large batches even though the model is only 137M params. This repo adds two attention paths…

Open weights mit 137M parameters sentence-transformers

[View model](https://savrn.com/models/coderankembed-flash-attn)

## 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 2026-09-26.
- [Hugging Face profile](https://huggingface.co/handwoven8588)
- [How the hub is built](https://savrn.com/model-hub/methodology)