@eeuhn fine-tuned a legal decision model with Unsloth’s notebook to classify trademarks on the Abercrombie spectrum, hitting 75.8% on LegalBench.

Ian @eeuhn

2026-10-11EN

56 views
1 likes
1 bookmarks
0 reposts

I'm like legal Jev pilled after using Unsloth's train-your-own-Jev model notebook. I made a legal Jev to classify trademarks under the Abercrombie spectrum. Tra…

About this case

Train result. Post reports ~7 minutes on one Colab G4; LegalBench Abercrombie scores: base Qwen3.5-4b 40.0%, earlier GRPO 68.4%, Unsloth custom Jev 75.8%. Links HF model/dataset DoodDood/abercrombie-decision. Text-only; verified via fxtwitter.

Original posthttps://x.com/eeuhn/status/2109422224188780768

Related cases

@Matthewagi trained TERN-35B-A3B to try decision models. On an H100 PCIe it reached $0.0116/Mtok, then $0.00773/Mtok on the cost-score Pareto frontier.@Matthewagi
@UnslothAI released a free notebook to train your own decision model so Qwen3.5-4B answers decisions instead of text on 8GB VRAM locally.@UnslothAI
@nutlope links an article titled “How to train your own Jev for $17.”@nutlope
@nutlope trained Tev1 0.8B, a tiny Jev-like classifier, and shows it classifying tasks locally on a Mac with Ollama at about 50ms end to end. Weights and benchmarks are said to be coming soon.@nutlope