Video-Text-to-Text
Transformers
Safetensors
llava_next_video
image-text-to-text
llava
video
sign-language
multimodal
Instructions to use Remostart/sign-language with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Remostart/sign-language with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Remostart/sign-language") model = AutoModelForMultimodalLM.from_pretrained("Remostart/sign-language", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "image_processor": { | |
| "crop_size": { | |
| "height": 336, | |
| "width": 336 | |
| }, | |
| "do_center_crop": true, | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_pad": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_grid_pinpoints": [ | |
| [ | |
| 336, | |
| 672 | |
| ], | |
| [ | |
| 672, | |
| 336 | |
| ], | |
| [ | |
| 672, | |
| 672 | |
| ], | |
| [ | |
| 1008, | |
| 336 | |
| ], | |
| [ | |
| 336, | |
| 1008 | |
| ] | |
| ], | |
| "image_mean": [ | |
| 0.48145466, | |
| 0.4578275, | |
| 0.40821073 | |
| ], | |
| "image_processor_type": "LlavaNextImageProcessor", | |
| "image_std": [ | |
| 0.26862954, | |
| 0.26130258, | |
| 0.27577711 | |
| ], | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "shortest_edge": 336 | |
| } | |
| }, | |
| "image_token": "<image>", | |
| "num_additional_image_tokens": 1, | |
| "patch_size": 14, | |
| "processor_class": "LlavaNextVideoProcessor", | |
| "video_processor": { | |
| "crop_size": { | |
| "height": 336, | |
| "width": 336 | |
| }, | |
| "data_format": "channels_first", | |
| "default_to_square": false, | |
| "do_center_crop": true, | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_pad": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "do_sample_frames": false, | |
| "image_grid_pinpoints": [ | |
| [ | |
| 336, | |
| 672 | |
| ], | |
| [ | |
| 672, | |
| 336 | |
| ], | |
| [ | |
| 672, | |
| 672 | |
| ], | |
| [ | |
| 1008, | |
| 336 | |
| ], | |
| [ | |
| 336, | |
| 1008 | |
| ] | |
| ], | |
| "image_mean": [ | |
| 0.48145466, | |
| 0.4578275, | |
| 0.40821073 | |
| ], | |
| "image_std": [ | |
| 0.26862954, | |
| 0.26130258, | |
| 0.27577711 | |
| ], | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "return_metadata": false, | |
| "size": { | |
| "shortest_edge": 336 | |
| }, | |
| "video_processor_type": "LlavaNextVideoVideoProcessor" | |
| }, | |
| "video_token": "<video>", | |
| "vision_feature_select_strategy": "default" | |
| } | |