Transformers
Safetensors
vision-language
document-understanding
boundingdocs
bitsandbytes
8-bit precision
Instructions to use CompressingVLM/glm-ocr-boundingdocs-ft-bnb-int8 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-int8 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("CompressingVLM/glm-ocr-boundingdocs-ft-bnb-int8", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download benchmark_loader_manifest.json from CompressingVLM/glm-ocr-boundingdocs-ft-bnb-int8: direct link, hf CLI and curl.
- Browser
- Download file 417 Bytes
-
https://huggingface.co/CompressingVLM/glm-ocr-boundingdocs-ft-bnb-int8/resolve/main/benchmark_loader_manifest.json
- Command line
-
hf download hf://CompressingVLM/glm-ocr-boundingdocs-ft-bnb-int8/benchmark_loader_manifest.json
-
curl -L -o benchmark_loader_manifest.json https://huggingface.co/CompressingVLM/glm-ocr-boundingdocs-ft-bnb-int8/resolve/main/benchmark_loader_manifest.json
417 Bytes
| { | |
| "quantization": "bitsandbytes", | |
| "bits": 8, | |
| "load_in_8bit": true, | |
| "load_in_4bit": false, | |
| "bnb_4bit_quant_type": null, | |
| "bnb_4bit_use_double_quant": null, | |
| "bnb_4bit_compute_dtype": null, | |
| "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" | |
| } |