Update README.md

README.md

@@ -12,7 +12,7 @@ tags:
 
 # DatologyAI CLIP Classification Optimized ViT-B/32
 
-**DatologyAI CLIP** is a state-of-the-art vision-language model that achieves superior performance through advanced data curation alone, without any architectural modifications. This classification-optimized ViT-B/32 model outperforms SigLIP2, MetaCLIP, and DFN on zero-shot classification benchmarks.
+**DatologyAI CLIP** is a state-of-the-art contrastive vision-language model that achieves superior performance through advanced data curation alone, without any architectural or training modifications. This classification-optimized ViT-B/32 model outperforms SigLIP2, MetaCLIP, and DFN on zero-shot classification benchmarks.
 
 ## Model Description
 
@@ -96,7 +96,7 @@ The model uses standard CLIP training objectives with no architectural modificat
 
 ## Training Data
 
-The model was trained on 13B image-text pairs curated from the **DataComp Extra-Large** dataset using DatologyAI's proprietary curation pipeline. The curation process selected high-quality, classification-relevant subsets from the 10B available pairs in DataComp-XL.
+The model was trained on 13B image-text (multi-epoch) curated from the **DataComp-XL** dataset using DatologyAI's proprietary curation pipeline. The curation process selected high-quality, classification-relevant subsets from the 10B available pairs in DataComp-XL.
 
 ## Evaluation Results
 
@@ -136,7 +136,7 @@ The model was trained on 13B image-text pairs curated from the **DataComp Extra-
 - **Weight decay:** 0.1
 - **Batch size:** 32,768
 - **Training samples:** 13B image-text pairs
-- **Hardware:** Distributed training on A100 GPUs
+- **Hardware:** Distributed training on H100 GPUs
 
 ## Citation