implementation detail · filed under training objective
SigLIP sigmoid contrastive loss
Also called sigmoid contrastive loss.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
we optimize the model using the sigmoid contrastive loss introduced by SigLIP (Zhai et al., 2023)
usedunclearin DeepSeek-V4.1-FlashDeepSeek