HopitAI
/

moda-pro-lite

@@ -84,14 +84,14 @@ Plain bi-encoder: one 768-d vector per image, one per query, cosine similarity.
 ## What's inside (summary)
 - **Base:** SigLIP2-base-384 (`timm/ViT-B-16-SigLIP2-384`), full fine-tune of both towers.
-- **Size — 213,159,938 params:** the base's 256K-token multilingual vocabulary is trimmed to the 44,646 pieces fashion text actually uses (BPE merge-closure preserved). Verified: **100.00% bit-identical** outputs on 12,000 benchmark queries and 6,000 held-out registers vs the untrimmed 375M model — every benchmark number in this card transfers exactly. Out-of-vocabulary input (emoji, non-Latin scripts, rare typos) re-segments gracefully into kept pieces (cosine 0.82–0.97 to full model), never a silent failure.
 - **Data:** 93K commercial product images (from [Marqo-GS-10M](https://huggingface.co/datasets/Marqo/marqo-GS-10M), Apache-2.0), re-annotated by a frontier VLM with graded relevance labels (99.9% coverage).
 - **Training:** a proprietary fine-tuning recipe; the pipeline and annotated dataset are not released.
 - **Distinctive property:** unlike typical fashion fine-tunes, Pro Lite does **not** collapse out of domain — it adds fashion skill while keeping generalist behavior (image-tower drift from base: 0.36%).
 ## Evaluation protocol
-Measured on six academic fashion benchmarks (DeepFashion In-Shop, DeepFashion Multimodal, Fashion200K, Polyvore, Atlas, KAGL) at **full corpus** — no gallery subsampling — plus H&M (10K, MRR) and ZooClaw-Fashion (12K, MAP@10), all through one open harness with identical preprocessing per model. Where Pro Lite loses (instance retrieval, caption-register sets), the card for [MODA](https://huggingface.co/HopitAI/moda-fashionsiglip-multiview-203m) shows the stronger pick — see the [full comparison](https://hopit-ai.github.io/Moda/) rather than a cherry-picked subset.
 ## Citation

 ## What's inside (summary)
 - **Base:** SigLIP2-base-384 (`timm/ViT-B-16-SigLIP2-384`), full fine-tune of both towers.
+- **Size — 213,159,938 params:** the base's 256K-token multilingual vocabulary is trimmed to the 44,646 pieces fashion text actually uses (BPE merge-closure preserved). Verified: **100.00% bit-identical** outputs on 12,000 benchmark queries and 6,000 held-out fashion texts vs the untrimmed 375M model — every benchmark number in this card transfers exactly. Out-of-vocabulary input (emoji, non-Latin scripts, rare typos) re-segments gracefully into kept pieces (cosine 0.82–0.97 to full model), never a silent failure.
 - **Data:** 93K commercial product images (from [Marqo-GS-10M](https://huggingface.co/datasets/Marqo/marqo-GS-10M), Apache-2.0), re-annotated by a frontier VLM with graded relevance labels (99.9% coverage).
 - **Training:** a proprietary fine-tuning recipe; the pipeline and annotated dataset are not released.
 - **Distinctive property:** unlike typical fashion fine-tunes, Pro Lite does **not** collapse out of domain — it adds fashion skill while keeping generalist behavior (image-tower drift from base: 0.36%).
 ## Evaluation protocol
+Measured on six academic fashion benchmarks (DeepFashion In-Shop, DeepFashion Multimodal, Fashion200K, Polyvore, Atlas, KAGL) at **full corpus** — no gallery subsampling — plus H&M (10K, MRR) and ZooClaw-Fashion (12K, MAP@10), all through one open harness with identical preprocessing per model. Where Pro Lite loses (instance retrieval, caption-style sets), the card for [MODA](https://huggingface.co/HopitAI/moda-fashionsiglip-multiview-203m) shows the stronger pick — see the [full comparison](https://hopit-ai.github.io/Moda/) rather than a cherry-picked subset.
 ## Citation