Model reference · open weights
marqo-fashionSigLIP is an open-weight embedding model from Marqo, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Marqo-FashionSigLIP Model Card [](https://github.com/marqo-ai/marqo-FashionCLIP) Marqo Fashion Siglip 2 is available. marqo-fashion-SigLip-2 has shown a further 78% improvement in MMR and recall vs marqo-fashion-SigLip. Contact Marqo to learn more: https://www.marqo.ai/book-demo Marqo-FashionSigLIP is a multimodal embedding model that provides up to 57% improvement in MRR and recall over fashion clip. Marqo-FashionSigLIP leverages Generalised Contrastive Learning (GCL) which allows the model to be trained on not just text descriptions but also categories, style, colors, materials, keywords and fine-details to provide highly relevant search results on fashion products. The model was fine-tuned from ViT-B-16-SigLIP (webli). Github Page: Marqo-FashionCLIP Blog: Marqo Blog Usage Hugging Face The model can be loaded with AutoModel by OpenCLIP The model can be seamlessly used with OpenCLIP by Transformers.js You can also run the model in JavaScript with the Transformers.js library. First, install it from NPM using: Then, compute embeddings as follows: Benchmark Results Average evaluation results on 6 public multimodal fashion datasets (Atlas, DeepFashion (In-shop), DeepFashion (Multimodal), Fashion200k, KAGL, and Polyvore) are reported below: Text-To-Image (Averaged across 6 datasets) Category-To-Product (Averaged across 5 datasets) Sub-Category-To-Product (Averaged across 4 datasets)
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | Marqo |
|---|---|
| Type | Embedding models |
| Parameters (lead) | 203M |
| Variants | 1 |
| Runs with | open_clip |
| Released | 2024-08-09 |
| Popularity | 356k downloads / month |
| Likes | 88 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| marqo-fashionSigLIP | 203M | BF16 | ~0.5 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys marqo-fashionsiglip for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (marqo-fashionsiglip below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/embeddings \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"marqo-fashionsiglip","input":"text to embed"}'
Details
Languages
Tags
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗
Explore