A recommender model looks at what people already bought and viewed and suggests what comes next. Unlike a cloud service, an open model learns from your own order history and stays inside your perimeter. Quality here depends less on the model than on how clean your purchase and view data is.
An open foundation model for recommendations from a short-video service: browsing and purchase history is fed to the model as a sequence and it predicts the next item or clip. Fine-tuning on your own data is required.
A small open generative recommender at 1.5B with published checkpoints and a full training pipeline. Handy as a learning and starter option; a real store needs fine-tuning on its own orders.
A two-level design: one language model reads the item description, the second builds the shopper interest from history. Ready checkpoints at 1B and 7B are published, but they need fine-tuning for your own catalogue.
Models that turn a product photo and its title into a single vector: suitable for a similar-items block, image search and matching by description. Built for retail product cards.
Description encoders trained so that items people actually buy together end up close to each other, not merely items that sound alike. Versions trained on public catalogues are published.
Encoders that put a text portrait of a shopper and a text description of an item into one vector space so they can be matched directly. They help where a new listing has no purchase statistics yet.
Three language models tuned on a large set of commerce instructions: product selection, answers from the item card, matching listings, review analysis. Your own assortment still needs fine-tuning.
Light encoders trained on pairs of item card and real review: they produce item vectors for similar-item blocks and for search by a shopper description. The weights are small and run on an ordinary server.
A 7B language model further trained on review and product-card text for recommendation and rating-prediction tasks. The licence forbids commercial use; a store still needs its own order history.
An approach where every item gets a short identifier code that a language model understands, and the model predicts that code. Delta weights for three categories are published; no licence is stated on the card.
A time-tested model for clothing and footwear: it places an item photo and its description in one space, so it fits similar-item blocks and outfit matching. Fine-tuning for your own assortment is advisable.
An early and still popular approach where recommendations are expressed as plain text: one small engine handles selection, rating and explanation. Checkpoints are trained on public datasets; a store needs its own.
An open model can run on your own server: data stays in-house, there is no per-request fee, and the model can be fine-tuned on your documents.
