Model reference · open weights
vqvae is an open-weight embedding model from hpcai-tech. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Maker | hpcai-tech |
|---|---|
| Type | Embedding models |
| Task | Embeddings |
| Parameters (lead) | 22M |
| Runs with | transformers |
| Released | 2024-02-20 |
| Popularity | 10 downloads / month |
| Licence | Open weights |
About
This repository is a clone of the VideoGPT in order to convert the VQ-VAE model to the Hugging Face format for easier model loading.
Paper: VideoGPT: Video Generation using VQ-VAE and Transformers
We follow the MIT license distributed by the VideoGPT project.
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys vqvae for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (vqvae 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":"vqvae","input":"text to embed"}'
Create an account — your API key is available in the console. 5M tokens/month currently included with every new account at launch.