Visual Question Answering
Transformers
Safetensors
Chinese
English
qwen3_vl
image-text-to-text
Docision
document-understanding
candidate-scoring
qwen3-vl
Instructions to use SoMarkAI/Docision-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SoMarkAI/Docision-1.0 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "visual-question-answering" 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("visual-question-answering", model="SoMarkAI/Docision-1.0")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("SoMarkAI/Docision-1.0") model = AutoModelForMultimodalLM.from_pretrained("SoMarkAI/Docision-1.0", device_map="auto") - Notebooks
- Google Colab
- Kaggle
docs: fix local model directory capitalization
Browse files
README.md
CHANGED
|
@@ -83,10 +83,10 @@ cd docision
|
|
| 83 |
python3 -m venv .venv
|
| 84 |
source .venv/bin/activate
|
| 85 |
python -m pip install -e '.' huggingface_hub
|
| 86 |
-
hf download SoMarkAI/Docision-1.0 --local-dir models/
|
| 87 |
|
| 88 |
CUDA_VISIBLE_DEVICES=0 python demo_docision.py \
|
| 89 |
-
--model models/
|
| 90 |
--input examples/multiple.json \
|
| 91 |
--output outputs/document-decisions.json
|
| 92 |
```
|
|
|
|
| 83 |
python3 -m venv .venv
|
| 84 |
source .venv/bin/activate
|
| 85 |
python -m pip install -e '.' huggingface_hub
|
| 86 |
+
hf download SoMarkAI/Docision-1.0 --local-dir models/Docision-1.0
|
| 87 |
|
| 88 |
CUDA_VISIBLE_DEVICES=0 python demo_docision.py \
|
| 89 |
+
--model models/Docision-1.0 \
|
| 90 |
--input examples/multiple.json \
|
| 91 |
--output outputs/document-decisions.json
|
| 92 |
```
|