Add link to Cosmos Tokenizer README in NeMo repo.
Browse files
README.md
CHANGED
|
@@ -223,6 +223,8 @@ model = CausalVideoTokenizer.from_pretrained(model_name)
|
|
| 223 |
input_tensor = torch.randn(1, 3, 9, 512, 512).to('cuda').to(torch.bfloat16)
|
| 224 |
(indices, codes) = model.encode(input_tensor)
|
| 225 |
```
|
|
|
|
|
|
|
| 226 |
|
| 227 |
# Evaluation
|
| 228 |
|
|
|
|
| 223 |
input_tensor = torch.randn(1, 3, 9, 512, 512).to('cuda').to(torch.bfloat16)
|
| 224 |
(indices, codes) = model.encode(input_tensor)
|
| 225 |
```
|
| 226 |
+
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 Tokenizer.
|
| 227 |
+
|
| 228 |
|
| 229 |
# Evaluation
|
| 230 |
|