Train your own Jev-like classifier for $17 with Qwen3.5 4B fine-tuning
nutlope · x · 2026-09-24
Together AI launched a tutorial and an open experimental model, together/Tev1-4B-experimental, fine-tuned on top of Qwen3.5 4B to replicate the Jev-style classifier.
- Jev-type models take a state plus predefined questions and quickly return a score, boolean, or multiple-choice answer — fast and extremely cheap to run
- The blog walks through the full fine-tuning process at a total cost of about $17
- Use cases include automated e-commerce return evaluation, ML paper categorization, and text sentiment scoring
More from Models
- Robot build test: GPT-6 Astra stabilizes two-board structure, Claude Fable 5.2 falls short — qinzytech · 2026-11-12
- Zvi dissects Anthropic's latest system card, disputing the autonomy threshold call — Don't Worry About the Vase (Zvi) · 2026-11-12
- Unsloth ships Qwen3.8-27B Dynamic V3.1 GGUFs with 5-10% accuracy gains — danielhanchen · 2026-11-12
- antirez backs low-bit DeepSeek 4.1 Flash over Qwen 27B dense on Apple M5 Macs — antirez · 2026-11-12
- Gemini re-renders images as text when vision is removed, dropping only 6% WSR — zacharynado · 2026-11-12
- Bare-harness coding benchmark: Fable 5.2 best overall, Gemini 4 Carbon best value — Semantic_meaning · 2026-11-12