laion/CLIP-ViT-H-14-laion2B-s32B-b79K
Primitive: /encode · Encode ·
CLIP
1. Model Details 3. Training Details 4. Evaluation 5. Acknowledgements 6. Citation 7. How To Get Started With the Model
MultimodalDense
View on Hugging Face → Guide: CLIP ViT-H/14 LAION-2B guide →
Overview
Hardware: — drives latency, throughput & cost
| Size | 986M params |
|---|---|
| Tasks | /encode |
| License | mit |
| Latency | 353 ms |
| Throughput | 438 tok/s |
| Cost | $0.508 /1M tok |
Cost is approximate — computed from list GPU prices; your actual price depends on the provider you deploy SIE with.
Embedding
| Output types | Dense |
|---|---|
| Dimensions | dense: 1,024 |
| Max sequence length | 77 |
| Inputs | text · image |
Benchmarks
Flickr30kI2TRetrieval
Image-to-text retrieval: retrieve captions from images
Corpus: 31,783 Queries: 1,000
Quality
ndcg at 10 0.8624
map at 10 0.7856
mrr at 10 0.9488
Performance L4-SPOT b1 c8
Corpus 181 tok/s
Corpus p50 533.4ms
Query 10.2 img/s
Query p50 625.9ms
Performance L4 b1 c16
Corpus 695 tok/s
Corpus p50 172.6ms
Query 10.1 mpix/s
Query p50 141.9ms
Compare (0)Compare →