Object Detection
Transformers
Safetensors
rt_detr_v2
document-layout-analysis
finance
rtdetr-v2
cuda
tf32
Instructions to use AutomatosX/AXDocLayout-M-v1.5-CUDA-TF32 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AutomatosX/AXDocLayout-M-v1.5-CUDA-TF32 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("object-detection", model="AutomatosX/AXDocLayout-M-v1.5-CUDA-TF32")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForObjectDetection tokenizer = AutoTokenizer.from_pretrained("AutomatosX/AXDocLayout-M-v1.5-CUDA-TF32") model = AutoModelForObjectDetection.from_pretrained("AutomatosX/AXDocLayout-M-v1.5-CUDA-TF32", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Publish owner-selected H5.1 as v1.5 with qualified CUDA profile and preserved tradeoffs
6536f3b verified Download NOTICE from AutomatosX/AXDocLayout-M-v1.5-CUDA-TF32: direct link, hf CLI and curl.
- Browser
- Download file 312 Bytes
-
https://huggingface.co/AutomatosX/AXDocLayout-M-v1.5-CUDA-TF32/resolve/main/NOTICE
- Command line
-
hf download hf://AutomatosX/AXDocLayout-M-v1.5-CUDA-TF32/NOTICE
-
curl -L -o NOTICE https://huggingface.co/AutomatosX/AXDocLayout-M-v1.5-CUDA-TF32/resolve/main/NOTICE
312 Bytes
| AX-DocLayout-M v1.5 (H5.1), owner-selected release, 2026. | |
| Derived from docling-project/docling-layout-heron revision | |
| 8f39ad3c0b4c58e9c2d2c84a38465abf757272d8 under Apache-2.0. | |
| Changes: H1/H5 finance tuning, paired H5.1 Title sampling and AX PDF SDK binding. | |
| No training documents or rendered pages are included. | |