Commit History
-
Fix transformers 5.x API change: get_text_features now returns BaseModelOutputWithPooling
Verified signatureIn transformers >=5.0, CLIPModel.get_text_features and get_image_features return BaseModelOutputWithPooling instead of a Tensor. The projected text/image embedding lives at .pooler_output (after projection). Add backward-compatible accessor that works on both old (tensor) and new (output object) return types.5e31798 -
Initial release: DW-KhotTaeVL-2B-QueryFrames v1.0
Verified signatureQuery-aware frame selection wrapper for Qwen3-VL-2B-Instruct. Wild mode: 64.3% on Video-MME mini 300Q (+7.3pp vs stock 57.0%). Benchmark mode: 66.3% (+9.3pp), 12/12 task buckets non-negative. Zero trainable parameters, no model weights modified. Built on Qwen/Qwen3-VL-2B-Instruct (Apache 2.0). Frame scorer: openai/clip-vit-large-patch14 (MIT). Author: Deaw (HF: @commandeaw).84c8a9d