Instructions to use nvidia/Cosmos3-Edge with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Cosmos
How to use nvidia/Cosmos3-Edge 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
- Notebooks
- Google Colab
- Kaggle
| { | |
| "allow_patterns_overrides": [ | |
| "*/*.safetensors" | |
| ], | |
| "architectures": [ | |
| "Cosmos3EdgeForConditionalGeneration" | |
| ], | |
| "image_token_id": 19, | |
| "model_type": "cosmos3_edge", | |
| "projector_config": { | |
| "input_hidden_size": 1152, | |
| "merger_intermediate_size": 11520, | |
| "model_type": "cosmos3_edge_projector", | |
| "out_hidden_size": 2048, | |
| "spatial_merge_size": 2, | |
| "use_postshuffle_norm": false | |
| }, | |
| "projector_hidden_size": 11520, | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 11, | |
| "head_dim": 128, | |
| "hidden_act": "relu2", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 9216, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "cosmos3_edge_text", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_parameters": { | |
| "mrope_section": [ | |
| 24, | |
| 20, | |
| 20 | |
| ], | |
| "rope_theta": 100000000, | |
| "rope_type": "default" | |
| }, | |
| "use_cache": true, | |
| "vocab_size": 131072 | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.57.1", | |
| "video_token_id": 18, | |
| "vision_config": { | |
| "attention_dropout": 0.0, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "intermediate_size": 4304, | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "cosmos3_edge_vision", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 27, | |
| "num_patches": 256, | |
| "patch_size": 16, | |
| "spatial_merge_size": 2 | |
| }, | |
| "vision_end_token_id": 21, | |
| "vision_start_token_id": 20 | |
| } | |