Feature Extraction
Transformers
Safetensors
English
qwen2_vl
image-text-to-text
multimodal
video embedding
ncsoft
ncai
varco
Instructions to use OpenLLM-Korea/GME-VARCO-VISION-Embedding with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenLLM-Korea/GME-VARCO-VISION-Embedding with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="OpenLLM-Korea/GME-VARCO-VISION-Embedding")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("OpenLLM-Korea/GME-VARCO-VISION-Embedding") model = AutoModelForMultimodalLM.from_pretrained("OpenLLM-Korea/GME-VARCO-VISION-Embedding", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download video_preprocessor_config.json from OpenLLM-Korea/GME-VARCO-VISION-Embedding: direct link, hf CLI and curl.
- Browser
- Download file 1.77 kB
-
https://huggingface.co/OpenLLM-Korea/GME-VARCO-VISION-Embedding/resolve/main/video_preprocessor_config.json
- Command line
-
hf download hf://OpenLLM-Korea/GME-VARCO-VISION-Embedding/video_preprocessor_config.json
-
curl -L -o video_preprocessor_config.json https://huggingface.co/OpenLLM-Korea/GME-VARCO-VISION-Embedding/resolve/main/video_preprocessor_config.json
1.77 kB
| { | |
| "_valid_kwargs_names": [ | |
| "do_convert_rgb", | |
| "do_resize", | |
| "size", | |
| "size_divisor", | |
| "default_to_square", | |
| "resample", | |
| "do_rescale", | |
| "rescale_factor", | |
| "do_normalize", | |
| "image_mean", | |
| "image_std", | |
| "do_pad", | |
| "do_center_crop", | |
| "crop_size", | |
| "data_format", | |
| "input_data_format", | |
| "device", | |
| "min_pixels", | |
| "max_pixels", | |
| "patch_size", | |
| "temporal_patch_size", | |
| "merge_size" | |
| ], | |
| "crop_size": null, | |
| "data_format": "channels_first", | |
| "default_to_square": true, | |
| "device": null, | |
| "do_center_crop": null, | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_pad": null, | |
| "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 | |
| ], | |
| "input_data_format": null, | |
| "max_pixels": 12845056, | |
| "merge_size": 2, | |
| "min_pixels": 3136, | |
| "model_valid_processing_keys": [ | |
| "do_convert_rgb", | |
| "do_resize", | |
| "size", | |
| "size_divisor", | |
| "default_to_square", | |
| "resample", | |
| "do_rescale", | |
| "rescale_factor", | |
| "do_normalize", | |
| "image_mean", | |
| "image_std", | |
| "do_pad", | |
| "do_center_crop", | |
| "crop_size", | |
| "data_format", | |
| "input_data_format", | |
| "device", | |
| "min_pixels", | |
| "max_pixels", | |
| "patch_size", | |
| "temporal_patch_size", | |
| "merge_size", | |
| "fps" | |
| ], | |
| "patch_size": 14, | |
| "processor_class": "Qwen2VLProcessor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "longest_edge": 12845056, | |
| "shortest_edge": 3136 | |
| }, | |
| "fps": 1.0, | |
| "num_frames": 8, | |
| "size_divisor": null, | |
| "temporal_patch_size": 2, | |
| "video_processor_type": "Qwen2VLVideoProcessor" | |
| } | |