Instructions to use BAAI/Emu3-VisionTokenizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BAAI/Emu3-VisionTokenizer with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="BAAI/Emu3-VisionTokenizer", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("BAAI/Emu3-VisionTokenizer", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from BAAI/Emu3-VisionTokenizer: direct link, hf CLI and curl.
- Browser
- Download file 592 Bytes
-
https://huggingface.co/BAAI/Emu3-VisionTokenizer/resolve/main/config.json
- Command line
-
hf download hf://BAAI/Emu3-VisionTokenizer/config.json
-
curl -L -o config.json https://huggingface.co/BAAI/Emu3-VisionTokenizer/resolve/main/config.json
592 Bytes
| { | |
| "architectures": [ | |
| "Emu3VisionVQModel" | |
| ], | |
| "attn_resolutions": [ | |
| 3 | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_emu3visionvq.Emu3VisionVQConfig", | |
| "AutoModel": "modeling_emu3visionvq.Emu3VisionVQModel" | |
| }, | |
| "ch": 256, | |
| "ch_mult": [ | |
| 1, | |
| 2, | |
| 2, | |
| 4 | |
| ], | |
| "codebook_size": 32768, | |
| "double_z": false, | |
| "dropout": 0.0, | |
| "embed_dim": 4, | |
| "in_channels": 3, | |
| "model_type": "Emu3VisionVQ", | |
| "num_res_blocks": 2, | |
| "out_channels": 3, | |
| "temporal_downsample_factor": 4, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.44.0", | |
| "z_channels": 4 | |
| } | |