Instructions to use npario/GLM-OCR-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use npario/GLM-OCR-bf16 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="npario/GLM-OCR-bf16")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("npario/GLM-OCR-bf16") model = AutoModelForMultimodalLM.from_pretrained("npario/GLM-OCR-bf16", device_map="auto") - MLX
How to use npario/GLM-OCR-bf16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir GLM-OCR-bf16 npario/GLM-OCR-bf16
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download processor_config.json from npario/GLM-OCR-bf16: direct link, hf CLI and curl.
- Browser
- Download file 597 Bytes
-
https://huggingface.co/npario/GLM-OCR-bf16/resolve/main/processor_config.json
- Command line
-
hf download hf://npario/GLM-OCR-bf16/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/npario/GLM-OCR-bf16/resolve/main/processor_config.json
597 Bytes
| { | |
| "image_processor": { | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.48145466, | |
| 0.4578275, | |
| 0.40821073 | |
| ], | |
| "image_processor_type": "Glm46VImageProcessor", | |
| "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": "GlmOcrProcessor" | |
| } | |