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: sync themed full-width tables and benchmark links
Browse files- README.md +15 -17
- assets/benchmark-table.en.dark.svg +13 -0
- assets/benchmark-table.en.svg +13 -0
- assets/model-table.en.dark.svg +10 -0
- assets/model-table.en.svg +10 -0
README.md
CHANGED
|
@@ -22,7 +22,7 @@ tags:
|
|
| 22 |
<p align="center"><b>Jev-Inspired Multimodal Decisions for Documents.</b></p>
|
| 23 |
<p align="center">
|
| 24 |
<a href="https://huggingface.co/SoMarkAI/Docision-1.0"><img src="assets/badge-model.svg" alt="Hugging Face: Docision" height="28"></a>
|
| 25 |
-
<a href="https://huggingface.co/datasets/
|
| 26 |
</p>
|
| 27 |
|
| 28 |
## 👀 Decision intelligence beyond text
|
|
@@ -44,14 +44,13 @@ Docision unifies document tasks through one simple interaction: Your Document. Y
|
|
| 44 |
|
| 45 |
## 🎯 Document decisions beyond a 27B model—higher speed, higher accuracy.
|
| 46 |
|
| 47 |
-
<
|
| 48 |
-
|
| 49 |
-
<
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
</
|
| 53 |
-
|
| 54 |
-
</div>
|
| 55 |
|
| 56 |
Covers **document understanding and decisions, and cross-industry classification**, with higher speed and quality.
|
| 57 |
|
|
@@ -64,14 +63,13 @@ Covers **document understanding and decisions, and cross-industry classification
|
|
| 64 |
|
| 65 |
## 🤗 Find our model here
|
| 66 |
|
| 67 |
-
<
|
| 68 |
-
|
| 69 |
-
<
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
</
|
| 73 |
-
|
| 74 |
-
</div>
|
| 75 |
|
| 76 |
<a id="start"></a>
|
| 77 |
|
|
|
|
| 22 |
<p align="center"><b>Jev-Inspired Multimodal Decisions for Documents.</b></p>
|
| 23 |
<p align="center">
|
| 24 |
<a href="https://huggingface.co/SoMarkAI/Docision-1.0"><img src="assets/badge-model.svg" alt="Hugging Face: Docision" height="28"></a>
|
| 25 |
+
<a href="https://huggingface.co/datasets/SoMarkAI/doc-decision-bench"><img src="assets/badge-benchmark.svg" alt="Benchmark: doc-decision-bench" height="28"></a>
|
| 26 |
</p>
|
| 27 |
|
| 28 |
## 👀 Decision intelligence beyond text
|
|
|
|
| 44 |
|
| 45 |
## 🎯 Document decisions beyond a 27B model—higher speed, higher accuracy.
|
| 46 |
|
| 47 |
+
<p align="center">
|
| 48 |
+
<a href="https://huggingface.co/datasets/SoMarkAI/doc-decision-bench"><picture>
|
| 49 |
+
<source media="(prefers-color-scheme: dark)" srcset="https://huggingface.co/SoMarkAI/Docision-1.0/resolve/main/assets/benchmark-table.en.dark.svg">
|
| 50 |
+
<source media="(prefers-color-scheme: light)" srcset="https://huggingface.co/SoMarkAI/Docision-1.0/resolve/main/assets/benchmark-table.en.svg">
|
| 51 |
+
<img src="assets/benchmark-table.en.svg" alt="doc-decision-bench: 5,234 document records. Open on Hugging Face." width="100%">
|
| 52 |
+
</picture></a>
|
| 53 |
+
</p>
|
|
|
|
| 54 |
|
| 55 |
Covers **document understanding and decisions, and cross-industry classification**, with higher speed and quality.
|
| 56 |
|
|
|
|
| 63 |
|
| 64 |
## 🤗 Find our model here
|
| 65 |
|
| 66 |
+
<p align="center">
|
| 67 |
+
<a href="https://huggingface.co/SoMarkAI/Docision-1.0"><picture>
|
| 68 |
+
<source media="(prefers-color-scheme: dark)" srcset="https://huggingface.co/SoMarkAI/Docision-1.0/resolve/main/assets/model-table.en.dark.svg">
|
| 69 |
+
<source media="(prefers-color-scheme: light)" srcset="https://huggingface.co/SoMarkAI/Docision-1.0/resolve/main/assets/model-table.en.svg">
|
| 70 |
+
<img src="assets/model-table.en.svg" alt="Docision-1.0: Open the model on Hugging Face." width="100%">
|
| 71 |
+
</picture></a>
|
| 72 |
+
</p>
|
|
|
|
| 73 |
|
| 74 |
<a id="start"></a>
|
| 75 |
|
assets/benchmark-table.en.dark.svg
ADDED
|
|
assets/benchmark-table.en.svg
ADDED
|
|
assets/model-table.en.dark.svg
ADDED
|
|
assets/model-table.en.svg
ADDED
|
|