Spaces:
Runtime error
Runtime error
Commit
•
5cd3b27
1
Parent(s):
0f8b50e
Update app.py
Browse files
app.py
CHANGED
@@ -6,15 +6,19 @@ markdownn = '''
|
|
6 |
# Text Classification Pipeline with DeepSparse
|
7 |
Text Classification involves assigning a label to a given text. For example, sentiment analysis is an example of a text classification use case.
|
8 |
![Text Classification Pipeline with DeepSparse](https://huggingface.co/spaces/neuralmagic/nlp-text-classification/resolve/main/text-classification.png)
|
9 |
-
|
10 |
DeepSparse is sparsity-aware inference runtime offering GPU-class performance on CPUs and APIs to integrate ML into your application. DeepSparse provides sparsified pipelines for computer vision and NLP.
|
11 |
-
The text classification Pipeline, for example, wraps an NLP model with the proper preprocessing and postprocessing pipelines, such as tokenization.
|
|
|
|
|
12 |
```
|
13 |
from deepsparse import Pipeline
|
14 |
pipeline = Pipeline.create(task="zero_shot_text_classification", model_path="zoo:nlp/text_classification/distilbert-none/pytorch/huggingface/mnli/pruned80_quant-none-vnni",model_scheme="mnli",model_config={"hypothesis_template": "This text is related to {}"},)
|
15 |
inference = pipeline(sequences= text,labels=['politics', 'public health', 'Europe'],)
|
16 |
print(inference)
|
17 |
```
|
|
|
|
|
18 |
'''
|
19 |
task = "zero_shot_text_classification"
|
20 |
dense_classification_pipeline = Pipeline.create(
|
|
|
6 |
# Text Classification Pipeline with DeepSparse
|
7 |
Text Classification involves assigning a label to a given text. For example, sentiment analysis is an example of a text classification use case.
|
8 |
![Text Classification Pipeline with DeepSparse](https://huggingface.co/spaces/neuralmagic/nlp-text-classification/resolve/main/text-classification.png)
|
9 |
+
## What is DeepSparse
|
10 |
DeepSparse is sparsity-aware inference runtime offering GPU-class performance on CPUs and APIs to integrate ML into your application. DeepSparse provides sparsified pipelines for computer vision and NLP.
|
11 |
+
The text classification Pipeline, for example, wraps an NLP model with the proper preprocessing and postprocessing pipelines, such as tokenization.
|
12 |
+
### Inference
|
13 |
+
Here is sample code for a text classification pipeline:
|
14 |
```
|
15 |
from deepsparse import Pipeline
|
16 |
pipeline = Pipeline.create(task="zero_shot_text_classification", model_path="zoo:nlp/text_classification/distilbert-none/pytorch/huggingface/mnli/pruned80_quant-none-vnni",model_scheme="mnli",model_config={"hypothesis_template": "This text is related to {}"},)
|
17 |
inference = pipeline(sequences= text,labels=['politics', 'public health', 'Europe'],)
|
18 |
print(inference)
|
19 |
```
|
20 |
+
## Resources
|
21 |
+
[Classify Even Longer Customer Reviews Using Sparsity with DeepSparse](https://neuralmagic.com/blog/accelerate-customer-review-classification-with-sparse-transformers/)
|
22 |
'''
|
23 |
task = "zero_shot_text_classification"
|
24 |
dense_classification_pipeline = Pipeline.create(
|