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

---

## Models

Model · Feature extraction

### [qwen3.5-4l-vocab40k-en-ko-headless](https://savrn.com/models/qwen3-5-4l-vocab40k-en-ko-headless)

[Junsung Kim](https://savrn.com/model-publishers/mp-juuuns)

A headless four-layer text backbone distilled from Qwen3.5-0.8B, with a vocabulary cut to English and Korean. It has no language-model head, no classification head, no labels and no thresholds. You attach a head and train it. This card is the record of how it was made. It walks the whole path — prompting the original model, turning it into a classifier, removing layers, changing precision, cutting the vocabulary, and cutting it again by rule — and shows what each step measured. We are not arguing that this model is better than anything. We built it, we measured it beside other models, and where we have a guess about why a number moved we say it is a guess. Every arm below was trained…

Open weights apache-2.0 121M parameters 262,144 tokens transformers

[View model](https://savrn.com/models/qwen3-5-4l-vocab40k-en-ko-headless)

## 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 2026-09-25.
- [Hugging Face profile](https://huggingface.co/mp-juuuns)
- [How the hub is built](https://savrn.com/model-hub/methodology)