Card: MODA Pro Lite (bare encoder); recipe moved to moda-pro-lite-plus

README.md

@@ -10,17 +10,15 @@ pipeline_tag: feature-extraction
 library_name: open_clip
 ---
 
-# MODA Pro Lite+
+# MODA Pro Lite
 
-**The strongest open system at ≤250M parameters on catalogue and title search.**
+A 213M fashion retrieval encoder (SigLIP2-base-384 backbone, fashion-vocabulary build).
+**Open weights.**
 
-MODA Pro Lite+ is a 213M fashion retrieval encoder (SigLIP2-base-384 backbone,
-fashion-vocabulary build) served with a calibrated multi-view recipe. Both ship here:
-the weights, and `serving_ann.py` which implements the recipe.
-
-The encoder on its own is **MODA Pro Lite**; with the recipe it is **MODA Pro Lite+**.
-Same weights, same repository, one extra step at index time and none at query time.
-Numbers for both are below.
+Served with its calibrated recipe it becomes
+**[MODA Pro Lite+](https://huggingface.co/HopitAI/moda-pro-lite-plus)** — the strongest open
+system at ≤250M parameters on catalogue and title search. The recipe lives in that repository;
+the weights live here, and Pro Lite+ pulls them at load time.
 
 ## Results
 
@@ -48,38 +46,12 @@ In-Shop queries average 75 words, and Pro Lite+ scores 0.1026 there against MODA
 If your queries are descriptions rather than titles, use
 [MODA Duo](https://huggingface.co/HopitAI/moda-duo), which routes per query.
 
-## Serving cost
-
-```
-stored vectors per item : 1
-ANN queries per search  : 1
-image forwards at index : 3x   offline, paid once
-text forwards per query : 2x   negligible beside the ANN probe
-```
-
-The recipe is a rule for *what you encode*, not a model change. Views are combined into one
-unit vector before indexing, so nearest-neighbour search costs exactly what the bare encoder
-costs — same index, same probe, no extra routes and no re-ranking.
-
 ## Use
 
 ```bash
-pip install open_clip_torch pillow numpy hnswlib
-python serving_ann.py --demo
-```
-
-```python
-from serving_ann import load, encode_images, encode_queries, build_index, search
-
-enc   = load()                          # open_clip, this repo's weights
-docs  = encode_images(catalogue, enc)   # (n, 768) float32, one vector per item
-index = build_index(docs)               # hnswlib, cosine via inner product
-qry   = encode_queries(["black leather ankle boots"], enc)
-ids, scores = search(index, qry, k=10)
+pip install open_clip_torch pillow
 ```
 
-Bare encoder, if you would rather not use the recipe:
-
 ```python
 import open_clip, torch
 
@@ -94,15 +66,8 @@ with torch.no_grad():
 ```
 
 768-d embeddings, cosine similarity, one vector per item. Index them in any vector database.
-
-## The recipe
-
-```
-document = normalize(official + 0.25 * square_pad + 0.25 * foreground_pad)
-query    = normalize(raw      + 0.25 * "a photo of {query}")
-```
-
-`serving_ann.py` implements it. Zero added parameters, one stored vector.
+For the recipe that lifts these numbers to the Pro Lite+ column, use
+[moda-pro-lite-plus](https://huggingface.co/HopitAI/moda-pro-lite-plus).
 
 ## Evaluation
 
@@ -112,6 +77,7 @@ All figures are full corpus, all ground-truth queries, MAP@10 under one evaluato
 
 ## Related
 
+- [MODA Pro Lite+](https://huggingface.co/HopitAI/moda-pro-lite-plus) — this encoder with its serving recipe.
 - [MODA Duo](https://huggingface.co/HopitAI/moda-duo) — routes each query to Pro Lite+ or MODA by its shape; beats both on a mixed workload.
 - [MODA](https://huggingface.co/HopitAI/moda-fashionsiglip-multiview-203m) — FashionSigLIP with a serving recipe. Stronger on long descriptions.
 - [MODA-SigLIP-Distilled](https://huggingface.co/HopitAI/moda-fashion-distilled) — image-to-image retrieval.