Model reference · open weights
CASA-Helium1-VL-Shared is an open-weight language model from kyutai. 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
| Released by | kyutai |
|---|---|
| Type | Language models |
| Task | Vision + text |
| Parameters (lead) | 2.7B |
| Context | 4k tokens |
| Runs with | transformers |
| Based on | kyutai/CASA-Helium1-VL-2B |
| Released | 2026-08-26 |
| Popularity | 9 downloads / month |
| Licence | Commercial licence needed |
About
This repository contains the model weights for CASA-Helium1-VL-2B-Shared, introduced in the paper CASA: Cross-Attention over Self-Attention for Efficient Vision-Language Fusion.
This is a variant of CASA-Helium1-VL-2B where the self-attention and cross-attention layers share the same parameters.
See CASA-Helium1-VL-2B for more information
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys casa-helium1-vl-shared for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (casa-helium1-vl-shared below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"casa-helium1-vl-shared","messages":[{"role":"user","content":"Hello"}]}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.