architectures · openai
Contrastive image-text dual encoder learning a joint embedding space (Radford et al., 2021). Foundation for zero-shot vision and diffusion conditioning.
| Weight file SHA-256 | 3d7d444bcdb3d33de138e42a1f2a6c932e2fcdc890c5a6c2db7dd70741572bcd |
|---|
| Publisher | openai |
|---|---|
| Origin | United States |
| Licence | MIT |
| Pulls recorded here | 142,001 |
Registry record as of 2026-06-06. Identity, licence and parameter count are properties of a release and do not move; tier can, and the verify link above re-checks it against the live registry rather than this page.