Model reference · open weights
tips-b14 is an open-weight embedding model from google, 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
TIPS — B/14 (v1) TIPS (Text-Image Pre-training with Spatial awareness, ICLR 2025) is a family of contrastive vision-language models that produce spatially rich image features aligned with text embeddings. This is the original (v1) B/14 release with 86M vision params and 110M text params, converted from the official checkpoints. Usage Load the model Encode images Images should be tensors in [0, 1] range (just ToTensor(), no ImageNet normalization). The second CLS token (out.registertokens) was trained on synthetic captions; the first (out.clstoken) on web alt-text, and is the one aligned with the text tower. Encode text Zero-shot classification Visualize spatial features Model details - ViT-B/14 vision encoder (12 layers, patch size 14, two CLS tokens) + 12-layer transformer text encoder - Native resolution 448; other patch-multiple resolutions work via positional-embedding interpolation - Preprocessing: images to [0, 1], no normalization; SentencePiece tokenizer, lowercased, max 64 tokens License Apache 2.0 Citation
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | |
|---|---|
| Type | Embedding models |
| Parameters (lead) | 196M |
| Variants | 1 |
| Runs with | transformers |
| Released | 2026-08-19 |
| Popularity | 255 downloads / month |
| Likes | 1 |
| 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 |
|---|---|---|---|---|---|
| tipsv1-b14 | 196M | BF16 | ~0.5 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys tips-b14 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (tips-b14 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":"tips-b14","input":"text to embed"}'
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗
Explore