Any-to-Any
Transformers
Safetensors
qwen2_5_vl
image-text-to-text
custom_code
text-generation-inference
Instructions to use modelscope/Nexus-GenV2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use modelscope/Nexus-GenV2 with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("modelscope/Nexus-GenV2", trust_remote_code=True) model = AutoModelForMultimodalLM.from_pretrained("modelscope/Nexus-GenV2", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from modelscope/Nexus-GenV2: direct link, hf CLI and curl.
- Browser
- Download file 575 Bytes
-
https://huggingface.co/modelscope/Nexus-GenV2/resolve/refs%2Fpr%2F3/preprocessor_config.json
- Command line
-
hf download hf://modelscope/Nexus-GenV2@refs/pr/3/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/modelscope/Nexus-GenV2/resolve/refs%2Fpr%2F3/preprocessor_config.json
575 Bytes
| { | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.48145466, | |
| 0.4578275, | |
| 0.40821073 | |
| ], | |
| "image_processor_type": "Qwen2VLImageProcessor", | |
| "image_std": [ | |
| 0.26862954, | |
| 0.26130258, | |
| 0.27577711 | |
| ], | |
| "max_pixels": 12845056, | |
| "merge_size": 2, | |
| "min_pixels": 3136, | |
| "patch_size": 14, | |
| "processor_class": "Qwen2_5_VLProcessor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "longest_edge": 12845056, | |
| "shortest_edge": 3136 | |
| }, | |
| "temporal_patch_size": 2 | |
| } | |