Update README.md

README.md

@@ -11,11 +11,34 @@ port of [cyclereward](https://github.com/hjbahng/cyclereward)
 
 There are three variants of the CycleReward model:
 1. CycleReward-Combo (This model)
-2. [CycleReward-I2T]()
-3. [CycleReward-T2I]()
+2. [CycleReward-I2T](https://huggingface.co/NagaSaiAbhinay/CycleReward-I2T)
+3. [CycleReward-T2I](https://huggingface.co/NagaSaiAbhinay/CycleReward-T2I)
 
 
 This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
 - Code: https://github.com/Abhinay1997/imscore, cyclereward branch
 - Paper: [2506.02095](https://arxiv.org/pdf/2506.02095)
-- Docs: [More Information Needed]
+- Docs: [More Information Needed]
+
+To use this model:
+- install imscore from my fork
+```bash
+pip install git+https://github.com/Abhinay1997/imscore@cyclereward
+```
+- use the model as follows
+```python
+from imscore.cyclereward.model import CycleReward
+available_models = ["NagaSaiAbhinay/CycleReward-Combo" "NagaSaiAbhinay/CycleReward-T2I", "NagaSaiAbhinay/CycleReward-I2T"]
+model_id = available_models[0]
+model = CycleReward.from_pretrained(model_id)
+
+prompts = "a photo of a cat"
+pixels = Image.open("cat.jpg")
+pixels = np.array(pixels)
+pixels = rearrange(torch.tensor(pixels), "h w c -> 1 c h w") / 255.0
+
+# prompts and pixels should have the same batch dimension
+# pixels should be in the range [0, 1]
+# score == logits
+score = model.score(pixels, prompts) # full differentiable reward)
+```