Qwen 3 VL - CATMuS Collection A collection of finetunes of Qwen 3 VL. These models were finetuned on the CATMuS dataset via TRL SFT. • 3 items • Updated 10 days ago • 2
small-models-for-glam/Qwen3-0.6B-SFT-name-parser-yaml Text Generation • 0.8B • Updated 18 days ago • 314 • 4
small-models-for-glam/Qwen3-0.6B-SFT-name-parser-yaml Text Generation • 0.8B • Updated 18 days ago • 314 • 4
view post Post 1045 I fine-tuned a smol VLM to generate specialized art history metadata!https://huggingface.co/davanstrien/iconclass-vlm: Qwen2.5-VL-3B trained using SFT to generate ICONCLASS codes (think Dewey Decimal for art!)Trained with TRL + HF Jobs - single UV script, no GPU needed! Space to explore predictions on a test set: davanstrien/iconclass-predictionsBlog soon! See translation 👍 2 2 + Reply