Instructions to use vastai-ais/GLM-OCR-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vastai-ais/GLM-OCR-FP8 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="vastai-ais/GLM-OCR-FP8")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("vastai-ais/GLM-OCR-FP8") model = AutoModelForMultimodalLM.from_pretrained("vastai-ais/GLM-OCR-FP8", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "image_processor": { | |
| "data_format": "channels_first", | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.48145466, | |
| 0.4578275, | |
| 0.40821073 | |
| ], | |
| "image_processor_type": "Glm46VImageProcessorFast", | |
| "image_std": [ | |
| 0.26862954, | |
| 0.26130258, | |
| 0.27577711 | |
| ], | |
| "merge_size": 2, | |
| "patch_size": 14, | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "longest_edge": 9633792, | |
| "shortest_edge": 12544 | |
| }, | |
| "temporal_patch_size": 2 | |
| }, | |
| "processor_class": "Glm46VProcessor", | |
| "video_processor": { | |
| "data_format": "channels_first", | |
| "default_to_square": true, | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "do_sample_frames": true, | |
| "fps": 2, | |
| "image_mean": [ | |
| 0.48145466, | |
| 0.4578275, | |
| 0.40821073 | |
| ], | |
| "image_processor_type": "Glm46VImageProcessor", | |
| "image_std": [ | |
| 0.26862954, | |
| 0.26130258, | |
| 0.27577711 | |
| ], | |
| "max_duration": 300, | |
| "max_image_size": { | |
| "longest_edge": 47040000 | |
| }, | |
| "merge_size": 2, | |
| "num_frames": 16, | |
| "patch_size": 14, | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "return_metadata": false, | |
| "size": { | |
| "longest_edge": 9633792, | |
| "shortest_edge": 12544 | |
| }, | |
| "temporal_patch_size": 2, | |
| "video_processor_type": "Glm46VVideoProcessor" | |
| } | |
| } | |