Add link to NeMo Cosmos Tokenizer directory

README.md

@@ -223,6 +223,8 @@ input_tensor = torch.randn(1, 3, 512, 512).to('cuda').to(torch.bfloat16)
 (latent, ) = model.encode(input_tensor)
 ```
 
+Please see the [Cosmos Tokenizer README within the NeMo repository](https://github.com/NVIDIA/NeMo/tree/main/nemo/collections/common/video_tokenizers) for additional examples to create training datasets with the Cosmos Tokenizers.
+
 # Evaluation
 
 ## TokenizationPerformance Comparison