KyutaiCASA
CASA Helium 1 VL 2B
This model combines Helium 1 text generation with a pretrained Qwen 2.5 VL vision encoder through cross-attention.
Research release
The architecture determines how images enter the model
CASA lets text attend to visual features without inserting every image token into the language sequence. The code supplies a custom architecture and processor; this is not an unchanged upstream Qwen or Helium checkpoint.CASA-Helium1-VL-2B: Kyutai model card
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Research release |
| Access | Downloadable |
| Model identifiers | kyutai/CASA-Helium1-VL-2B |
| Weight license | CC BY-NC-SA 4.0.CASA-Helium1-VL-2B: Kyutai model card |
| Upstream components | Helium 1 and a Qwen 2.5 VL encoder. Gemma terms and the Qwen Research License apply.CASA-Helium1-VL-2B: Kyutai model cardhelium-1-2b: Kyutai model cardCASA-Qwen2_5-VL-3B: Kyutai model card |
Related models
- Helium 1 VL 2B
Kyutai ยท CASA
An instruction-tuned vision-language reference model that inserts image tokens into the text sequence.
Launch date not confirmedResearch releaseDownloadable