Instructions to use nvidia/Cosmos-Embed1-224p with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Cosmos
How to use nvidia/Cosmos-Embed1-224p with Cosmos:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- NeMo
How to use nvidia/Cosmos-Embed1-224p with NeMo:
# tag did not correspond to a valid NeMo domain.
- Notebooks
- Google Colab
- Kaggle
Download config.json from nvidia/Cosmos-Embed1-224p: direct link, hf CLI and curl.
- Browser
- Download file 563 Bytes
-
https://huggingface.co/nvidia/Cosmos-Embed1-224p/resolve/refs%2Fpr%2F1/config.json
- Command line
-
hf download hf://nvidia/Cosmos-Embed1-224p@refs/pr/1/config.json
-
curl -L -o config.json https://huggingface.co/nvidia/Cosmos-Embed1-224p/resolve/refs%2Fpr%2F1/config.json
563 Bytes
| { | |
| "architectures": [ | |
| "CosmosEmbed1" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_embed1.CosmosEmbed1Config", | |
| "AutoProcessor": "preprocessing_embed1.CosmosEmbed1Processor", | |
| "AutoModel": "modeling_embed1.CosmosEmbed1" | |
| }, | |
| "embed_dim": 256, | |
| "max_txt_len": 128, | |
| "model_type": "cosmos-embed1", | |
| "num_query_tokens": 32, | |
| "num_video_frames": 8, | |
| "resolution": 224, | |
| "temporal_encoding_type": "neighboring_token_propagation", | |
| "transformers_version": "4.51.3", | |
| "vocab_size": 30523, | |
| "transformer_engine": false, | |
| "use_fp8": false | |
| } | |