CLIP · ViT-L/14 · Foundation Model
Transfer Learning Lab
Adapt the pretrained CLIP foundation model to specialized domains via LoRA adapters and contrastive fine-tuning.
⌘K
GPU78%
Loss0.184
Throughput312/s
Domain
Pipeline
Load CLIP
→Freeze backbone
→LoRA adapters
→Contrastive FT
→Evaluate
Medical · accuracy curves
Epoch 0 / 24
—