Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: distilbert/distilbert-base-uncased-distilled-squad
|
| 3 |
+
datasets:
|
| 4 |
+
- squad
|
| 5 |
+
language: en
|
| 6 |
+
license: apache-2.0
|
| 7 |
+
tags:
|
| 8 |
+
- openvino
|
| 9 |
+
widget:
|
| 10 |
+
- text: Which name is also used to describe the Amazon rainforest in English?
|
| 11 |
+
context: 'The Amazon rainforest (Portuguese: Floresta Amazônica or Amazônia; Spanish:
|
| 12 |
+
Selva Amazónica, Amazonía or usually Amazonia; French: Forêt amazonienne; Dutch:
|
| 13 |
+
Amazoneregenwoud), also known in English as Amazonia or the Amazon Jungle, is
|
| 14 |
+
a moist broadleaf forest that covers most of the Amazon basin of South America.
|
| 15 |
+
This basin encompasses 7,000,000 square kilometres (2,700,000 sq mi), of which
|
| 16 |
+
5,500,000 square kilometres (2,100,000 sq mi) are covered by the rainforest. This
|
| 17 |
+
region includes territory belonging to nine nations. The majority of the forest
|
| 18 |
+
is contained within Brazil, with 60% of the rainforest, followed by Peru with
|
| 19 |
+
13%, Colombia with 10%, and with minor amounts in Venezuela, Ecuador, Bolivia,
|
| 20 |
+
Guyana, Suriname and French Guiana. States or departments in four nations contain
|
| 21 |
+
"Amazonas" in their names. The Amazon represents over half of the planet''s remaining
|
| 22 |
+
rainforests, and comprises the largest and most biodiverse tract of tropical rainforest
|
| 23 |
+
in the world, with an estimated 390 billion individual trees divided into 16,000
|
| 24 |
+
species.'
|
| 25 |
+
- text: How many square kilometers of rainforest is covered in the basin?
|
| 26 |
+
context: 'The Amazon rainforest (Portuguese: Floresta Amazônica or Amazônia; Spanish:
|
| 27 |
+
Selva Amazónica, Amazonía or usually Amazonia; French: Forêt amazonienne; Dutch:
|
| 28 |
+
Amazoneregenwoud), also known in English as Amazonia or the Amazon Jungle, is
|
| 29 |
+
a moist broadleaf forest that covers most of the Amazon basin of South America.
|
| 30 |
+
This basin encompasses 7,000,000 square kilometres (2,700,000 sq mi), of which
|
| 31 |
+
5,500,000 square kilometres (2,100,000 sq mi) are covered by the rainforest. This
|
| 32 |
+
region includes territory belonging to nine nations. The majority of the forest
|
| 33 |
+
is contained within Brazil, with 60% of the rainforest, followed by Peru with
|
| 34 |
+
13%, Colombia with 10%, and with minor amounts in Venezuela, Ecuador, Bolivia,
|
| 35 |
+
Guyana, Suriname and French Guiana. States or departments in four nations contain
|
| 36 |
+
"Amazonas" in their names. The Amazon represents over half of the planet''s remaining
|
| 37 |
+
rainforests, and comprises the largest and most biodiverse tract of tropical rainforest
|
| 38 |
+
in the world, with an estimated 390 billion individual trees divided into 16,000
|
| 39 |
+
species.'
|
| 40 |
+
---
|
| 41 |
+
|
| 42 |
+
This model was converted to OpenVINO from [`distilbert/distilbert-base-uncased-distilled-squad`](https://huggingface.co/distilbert/distilbert-base-uncased-distilled-squad) using [optimum-intel](https://github.com/huggingface/optimum-intel)
|
| 43 |
+
via the [export](https://huggingface.co/spaces/echarlaix/openvino-export) space.
|
| 44 |
+
|
| 45 |
+
First make sure you have optimum-intel installed:
|
| 46 |
+
|
| 47 |
+
```bash
|
| 48 |
+
pip install optimum[openvino]
|
| 49 |
+
```
|
| 50 |
+
|
| 51 |
+
To load your model you can do as follows:
|
| 52 |
+
|
| 53 |
+
```python
|
| 54 |
+
from optimum.intel import OVModelForQuestionAnswering
|
| 55 |
+
|
| 56 |
+
model_id = "echarlaix/distilbert-base-uncased-distilled-squad-openvino"
|
| 57 |
+
model = OVModelForQuestionAnswering.from_pretrained(model_id)
|
| 58 |
+
```
|