A Jev-style model fine-tuned on Qwen3.5 4B

This weekend, I did a fun experiment to create something similar to Jev. I LoRA fine-tuned Qwen3.5 4B using a mix of publicly available datasets and synthetic data.

For the synthetic data, I used DeepSeek V4.1 Flash, around 25M tokens. I trained the model for about 2 hours on a rented RTX 3090.

So far, the model performs pretty well. It's obviously nowhere near Jev yet, but compared to the base model, it works surprisingly well (0.596 -> 0.709 on typed-decisions).

I've open-sourced everything, including the synthetic dataset and a Jev-compatible API endpoint, so you can try it here:

https://github.com/n4ze3m/hmm/

https://huggingface.co/n4ze3m/Qwen3.5-4B-Hmm

https://huggingface.co/datasets/n4ze3m/typed-decisions-synth