Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -5,20 +5,20 @@ license: apache-2.0
|
|
| 5 |
library_name: onnx
|
| 6 |
tags:
|
| 7 |
- onnx
|
| 8 |
-
-
|
| 9 |
base_model: facebook/bart-large-cnn
|
| 10 |
pipeline_tag: summarization
|
| 11 |
---
|
| 12 |
|
| 13 |
# Bart Large Cnn
|
| 14 |
|
| 15 |
-
|
| 16 |
|
| 17 |
## Model Details
|
| 18 |
|
| 19 |
- **Source Model**: [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn)
|
| 20 |
- **Format**: ONNX
|
| 21 |
-
- **Converted by**: [
|
| 22 |
|
| 23 |
## Usage
|
| 24 |
|
|
@@ -34,12 +34,12 @@ session = ort.InferenceSession("bart-large-cnn-onnx.onnx")
|
|
| 34 |
|
| 35 |
```python
|
| 36 |
from optimum.onnxruntime import ORTModelForSequenceClassification
|
| 37 |
-
model = ORTModelForSequenceClassification.from_pretrained("
|
| 38 |
```
|
| 39 |
|
| 40 |
-
## About
|
| 41 |
|
| 42 |
-
[
|
| 43 |
|
| 44 |
All conversions are optimized for edge deployment within browser and mobile memory constraints.
|
| 45 |
|
|
|
|
| 5 |
library_name: onnx
|
| 6 |
tags:
|
| 7 |
- onnx
|
| 8 |
+
- forkjoin-ai
|
| 9 |
base_model: facebook/bart-large-cnn
|
| 10 |
pipeline_tag: summarization
|
| 11 |
---
|
| 12 |
|
| 13 |
# Bart Large Cnn
|
| 14 |
|
| 15 |
+
Forkjoin.ai conversion of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) to ONNX format for edge deployment.
|
| 16 |
|
| 17 |
## Model Details
|
| 18 |
|
| 19 |
- **Source Model**: [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn)
|
| 20 |
- **Format**: ONNX
|
| 21 |
+
- **Converted by**: [Forkjoin.ai](https://forkjoin.ai)
|
| 22 |
|
| 23 |
## Usage
|
| 24 |
|
|
|
|
| 34 |
|
| 35 |
```python
|
| 36 |
from optimum.onnxruntime import ORTModelForSequenceClassification
|
| 37 |
+
model = ORTModelForSequenceClassification.from_pretrained("forkjoin-ai/bart-large-cnn-onnx")
|
| 38 |
```
|
| 39 |
|
| 40 |
+
## About Forkjoin.ai
|
| 41 |
|
| 42 |
+
[Forkjoin.ai](https://forkjoin.ai) runs AI models at the edge -- in-browser, on-device, zero cloud cost. These converted models power real-time inference, speech recognition, and natural language capabilities.
|
| 43 |
|
| 44 |
All conversions are optimized for edge deployment within browser and mobile memory constraints.
|
| 45 |
|