Balanced CLIP (1M)
Training CLIP-G took >15KwH of energy, CLIP-L took far less <1KwH
The full negative reinforcement (Cosine Dissimilarity) is available on my huggingface, this was paired with a positive reinforcement (Contrastive Loss) using the full frozen vision model in latent space.
Description
Details
Downloads
7
Platform
SeaArt
Platform Status
Available
Created
9/30/2025
Updated
10/2/2025
Deleted
-
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.