Instructions to use npario/GLM-OCR-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use npario/GLM-OCR-8bit 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-8bit")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("npario/GLM-OCR-8bit") model = AutoModelForMultimodalLM.from_pretrained("npario/GLM-OCR-8bit", device_map="auto") - MLX
How to use npario/GLM-OCR-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download npario/GLM-OCR-8bit --local-dir GLM-OCR-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download generation_config.json from npario/GLM-OCR-8bit: direct link, hf CLI and curl.
- Browser
- Download file 165 Bytes
-
https://huggingface.co/npario/GLM-OCR-8bit/resolve/main/generation_config.json
- Command line
-
hf download hf://npario/GLM-OCR-8bit/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/npario/GLM-OCR-8bit/resolve/main/generation_config.json
165 Bytes
| { | |
| "_from_model_config": true, | |
| "do_sample": false, | |
| "eos_token_id": [ | |
| 59246, | |
| 59253 | |
| ], | |
| "pad_token_id": 59246, | |
| "transformers_version": "5.0.1dev0" | |
| } | |