Transformers
Safetensors
vision-language
document-understanding
boundingdocs
bitsandbytes
4-bit precision
Instructions to use CompressingVLM/glm-ocr-boundingdocs-ft-bnb-nf4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CompressingVLM/glm-ocr-boundingdocs-ft-bnb-nf4 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("CompressingVLM/glm-ocr-boundingdocs-ft-bnb-nf4", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "quantization": "bitsandbytes", | |
| "bits": 4, | |
| "load_in_8bit": false, | |
| "load_in_4bit": true, | |
| "bnb_4bit_quant_type": "nf4", | |
| "bnb_4bit_use_double_quant": true, | |
| "bnb_4bit_compute_dtype": "bfloat16", | |
| "source_model": "/content/dce_checkpoints/gaycor/base_glm_ocr_unquantized", | |
| "adapter_path": "/content/dce_checkpoints/gaycor/checkpoint-8000", | |
| "model_kind": "gaycor_tit GLM-OCR LoRA fine-tuned checkpoint-8000" | |
| } |