Update README.md

README.md

@@ -14,12 +14,25 @@ SigLIP model pre-trained on WebLi at resolution 384x384. It was introduced in th
 
 Disclaimer: The team releasing SigLIP did not write a model card for this model so this model card has been written by the Hugging Face team.
 
+This model is a finetune for [DSTA BrainHack TIL 2024 competition](https://github.com/aliencaocao/TIL-2024).
+
 ## Model description
 
 SigLIP is [CLIP](https://huggingface.co/docs/transformers/model_doc/clip), a multimodal model, with a better loss function. The sigmoid loss operates solely on image-text pairs and does not require a global view of the pairwise similarities for normalization. This allows further scaling up the batch size, while also performing better at smaller batch sizes.
 
 A TLDR of SigLIP by one of the authors can be found [here](https://twitter.com/giffmana/status/1692641733459267713).
 
+`*.pth` files are converted TensorRT checkpoints in FP16, to be used via torch2trt:
+
+```
+from torch2trt import TRTModule()
+
+vision_trt = TRTModule()
+vision_trt.load_state_dict(torch.load('vision_trt.pth'))
+text_trt = TRTModule()
+text_trt.load_state_dict(torch.load('text_trt.pth'))
+```
+
 ## Intended uses & limitations
 
 You can use the raw model for tasks like zero-shot image classification and image-text retrieval. See the [model hub](https://huggingface.co/models?search=google/siglip) to look for