rename to nemotron
Browse files
README.md
CHANGED
|
@@ -14,24 +14,24 @@ tags:
|
|
| 14 |
- ingestion
|
| 15 |
- yolox
|
| 16 |
---
|
| 17 |
-
#
|
| 18 |
|
| 19 |
## **Model Overview**
|
| 20 |
|
| 21 |

|
| 22 |
*Preview of the model output on the example image.*
|
| 23 |
|
| 24 |
-
The input of this model is expected to be a chart image. You can use the [
|
| 25 |
|
| 26 |
### **Description**
|
| 27 |
|
| 28 |
-
The **
|
| 29 |
|
| 30 |
The model excels at detecting and localizing various graphic elements within chart images, including titles, axis labels, legends, and data point annotations. This capability makes it particularly valuable for document understanding tasks and automated data extraction from visual content.
|
| 31 |
|
| 32 |
This model is ready for commercial/non-commercial use.
|
| 33 |
|
| 34 |
-
We are excited to announce the open sourcing of this commercial model. For users interested in deploying this model in production environments, it is also available via the model API in NVIDIA Inference Microservices (NIM) at [
|
| 35 |
|
| 36 |
### License/Terms of use
|
| 37 |
|
|
@@ -52,7 +52,7 @@ Global
|
|
| 52 |
|
| 53 |
### Use Case
|
| 54 |
|
| 55 |
-
The **
|
| 56 |
- Enterprise document extraction, embedding and indexing
|
| 57 |
- Augmenting Retrieval Augmented Generation (RAG) workflows with multimodal retrieval
|
| 58 |
- Data extraction from legacy documents and reports
|
|
@@ -60,7 +60,7 @@ The **NeMo Retriever Graphic Elements v1** is designed for automating extraction
|
|
| 60 |
|
| 61 |
### Release Date
|
| 62 |
|
| 63 |
-
10/23/2025 via https://huggingface.co/nvidia/
|
| 64 |
|
| 65 |
### References
|
| 66 |
|
|
@@ -128,11 +128,11 @@ git lfs install
|
|
| 128 |
```
|
| 129 |
- Using https
|
| 130 |
```
|
| 131 |
-
git clone https://huggingface.co/nvidia/
|
| 132 |
```
|
| 133 |
- Or using ssh
|
| 134 |
```
|
| 135 |
-
git clone [email protected]:nvidia/
|
| 136 |
```
|
| 137 |
|
| 138 |
2. Run the model using the following code:
|
|
@@ -184,7 +184,7 @@ We provide examples in the notebook `Demo.ipynb`.
|
|
| 184 |
### Software Integration
|
| 185 |
|
| 186 |
**Runtime Engine(s):**
|
| 187 |
-
- **
|
| 188 |
|
| 189 |
|
| 190 |
**Supported Hardware Microarchitecture Compatibility [List in Alphabetic Order]:**
|
|
@@ -201,7 +201,7 @@ This AI model can be embedded as an Application Programming Interface (API) call
|
|
| 201 |
|
| 202 |
## Model Version(s):
|
| 203 |
|
| 204 |
-
* `
|
| 205 |
|
| 206 |
## Training and Evaluation Datasets:
|
| 207 |
|
|
|
|
| 14 |
- ingestion
|
| 15 |
- yolox
|
| 16 |
---
|
| 17 |
+
# Nemotron Graphic Element v1
|
| 18 |
|
| 19 |
## **Model Overview**
|
| 20 |
|
| 21 |

|
| 22 |
*Preview of the model output on the example image.*
|
| 23 |
|
| 24 |
+
The input of this model is expected to be a chart image. You can use the [Nemotron Page Element v3](https://huggingface.co/nvidia/nemotron-page-elements-v3) to detect and crop such images.
|
| 25 |
|
| 26 |
### **Description**
|
| 27 |
|
| 28 |
+
The **Nemotron Graphic Elements v1** model is a specialized object detection system designed to identify and extract key elements from charts and graphs. Based on YOLOX, an anchor-free version of YOLO (You Only Look Once), this model combines a simpler architecture with enhanced performance. While the underlying technology builds upon work from [Megvii Technology](https://github.com/Megvii-BaseDetection/YOLOX), we developed our own base model through complete retraining rather than using pre-trained weights.
|
| 29 |
|
| 30 |
The model excels at detecting and localizing various graphic elements within chart images, including titles, axis labels, legends, and data point annotations. This capability makes it particularly valuable for document understanding tasks and automated data extraction from visual content.
|
| 31 |
|
| 32 |
This model is ready for commercial/non-commercial use.
|
| 33 |
|
| 34 |
+
We are excited to announce the open sourcing of this commercial model. For users interested in deploying this model in production environments, it is also available via the model API in NVIDIA Inference Microservices (NIM) at [nemotron-graphic-elements-v1](https://build.nvidia.com/nvidia/nemotron-graphic-elements-v1).
|
| 35 |
|
| 36 |
### License/Terms of use
|
| 37 |
|
|
|
|
| 52 |
|
| 53 |
### Use Case
|
| 54 |
|
| 55 |
+
The **Nemotron Graphic Elements v1** is designed for automating extraction of graphic elements of charts in enterprise documents. Key applications include:
|
| 56 |
- Enterprise document extraction, embedding and indexing
|
| 57 |
- Augmenting Retrieval Augmented Generation (RAG) workflows with multimodal retrieval
|
| 58 |
- Data extraction from legacy documents and reports
|
|
|
|
| 60 |
|
| 61 |
### Release Date
|
| 62 |
|
| 63 |
+
10/23/2025 via https://huggingface.co/nvidia/nemotron-graphic-elements-v1
|
| 64 |
|
| 65 |
### References
|
| 66 |
|
|
|
|
| 128 |
```
|
| 129 |
- Using https
|
| 130 |
```
|
| 131 |
+
git clone https://huggingface.co/nvidia/nemotron-graphic-elements-v1
|
| 132 |
```
|
| 133 |
- Or using ssh
|
| 134 |
```
|
| 135 |
+
git clone [email protected]:nvidia/nemotron-graphic-elements-v1
|
| 136 |
```
|
| 137 |
|
| 138 |
2. Run the model using the following code:
|
|
|
|
| 184 |
### Software Integration
|
| 185 |
|
| 186 |
**Runtime Engine(s):**
|
| 187 |
+
- **Nemotron Page Elements v3** NIM
|
| 188 |
|
| 189 |
|
| 190 |
**Supported Hardware Microarchitecture Compatibility [List in Alphabetic Order]:**
|
|
|
|
| 201 |
|
| 202 |
## Model Version(s):
|
| 203 |
|
| 204 |
+
* `nemotron-graphic-elements-v1`
|
| 205 |
|
| 206 |
## Training and Evaluation Datasets:
|
| 207 |
|