All posts
Jun 24, 20264 min read
Tuned Tensor now supports fine-tuning Qwen/Qwen3-VL-2B-Instruct for OCR and document extraction workflows
Bring image and document-page inputs into a behavior-first fine-tuning workflow that turns visual documents into structured JSON.
Read postJun 20, 20264 min read
Fine-tune Qwen 3.5 2B for financial sentiment analysis
A public Hugging Face dataset, a strict JSON behavior spec, one Qwen3.5-2B fine-tune, local smoke tests, and a shipped model card.
Read postJun 14, 20263 min read
A new labeling loop for training data
A concrete finance-news labeling pass: 1,000 accepted rows, settled cost, review flow, provenance notes, and the spec bundled with the dataset.
Read postJun 8, 20266 min read
Fine-tune Qwen 3.5 2B for email safety triage
A public 10k-row Hugging Face dataset, a strict JSON safety spec, and one Qwen 3.5 2B fine-tune that triages email, flags phishing and spam, and blocks prompt-injection — with the dataset, model, and spec all published.
Read post