Model reference · open weights
gtr-t5-large is an open-weight embedding model from sentence-transformers, 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
sentence-transformers/gtr-t5-large This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space. The model was specifically trained for the task of sematic search. This model was converted from the Tensorflow model gtr-large-1 to PyTorch. When using this model, have a look at the publication: Large Dual Encoders Are Generalizable Retrievers. The tfhub model and this PyTorch model can produce slightly different embeddings, however, when run on the same benchmarks, they produce identical results. The model uses only the encoder from a T5-large model. The weights are stored in FP16. Usage (Sentence-Transformers) Using this model becomes easy when you have sentence-transformers installed: Then you can use the model like this: The model requires sentence-transformers version 2.2.0 or newer. Citing & Authors If you find this model helpful, please cite the respective publication: Large Dual Encoders Are Generalizable Retrievers
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | sentence-transformers |
|---|---|
| Type | Embedding models |
| Parameters (lead) | 335M |
| Context | 512 tokens |
| Variants | 1 |
| Runs with | sentence-transformers |
| Released | 2022-03-02 |
| Popularity | 57k downloads / month |
| Likes | 40 |
| 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 |
|---|---|---|---|---|---|
| gtr-t5-large | 335M | BF16 | ~0.8 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys gtr-t5-large for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (gtr-t5-large 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":"gtr-t5-large","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