| datasets: | |
| - OpenGVLab/InternVid | |
| base_model: | |
| - openai/clip-vit-large-patch14 | |
| tags: | |
| - ViCLIP | |
| huggingface weight of ViCLIP | |
| remember to set your `tokenizer_path` in config.json | |
| usage is in demo.ipynb |
| datasets: | |
| - OpenGVLab/InternVid | |
| base_model: | |
| - openai/clip-vit-large-patch14 | |
| tags: | |
| - ViCLIP | |
| huggingface weight of ViCLIP | |
| remember to set your `tokenizer_path` in config.json | |
| usage is in demo.ipynb |