https://github.com/Gigabyte0x1337/BERT-ML.NET

BERT Model for dotnet ML
https://github.com/Gigabyte0x1337/BERT-ML.NET

api bert-model dotnet ml

Last synced: 5 days ago
JSON representation

BERT Model for dotnet ML

• Host: GitHub
• URL: https://github.com/Gigabyte0x1337/BERT-ML.NET
• Owner: Gigabyte0x1337
• License: mit
• Created: 2019-09-10T20:21:02.000Z (about 5 years ago)
• Default Branch: master
• Last Pushed: 2021-08-10T17:31:23.000Z (over 3 years ago)
• Last Synced: 2023-03-06T05:48:12.404Z (over 1 year ago)
• Topics: api, bert-model, dotnet, ml
• Language: C#
• Homepage:
• Size: 177 KB
• Stars: 70
• Watchers: 5
• Forks: 12
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# BERT-ML.NET

Question and Answering (Q&A) BERT model implementation for ML.NET.

An example of BERT model predictions in .NET Core/.NET Standard.

## Model

https://github.com/onnx/models/tree/master/text/machine_comprehension/bert-squad

Download the pre-trained BERT ONNX model by running `getDependicies.sh`. Or download the [model](https://github.com/onnx/models/blob/master/text/machine_comprehension/bert-squad/model/bertsquad-10.onnx?raw=true) to the `BERT.WebApi/Model` folder.

## GPU usage

The project is setup to run on CPU. This allows the sample to run on machines without an Nvidia GPU.

To run on an Nvidia CUDA GPU:

* Set `hasGpu = true` in OnnxModelConfigurator.cs

* Remove NuGet `Microsoft.ML.OnnxRuntime.NoOpenMP`

* Add NuGet `Microsoft.ML.OnnxRuntime.Gpu`

## Example queries

When the solution runs, it will start an ASP.NET webservice at localhost:5001.

|    | Context | Question | Model Reply |

| -- | --  | -- | -- |

| ([link](https://localhost:5001/api/predict?Context=Bob%20is%20walking%20through%20the%20woods%20collecting%20blueberries%20and%20strawberries%20to%20make%20a%20pie.&Question=What%20is%20his%20name?)) | Bob is walking through the woods collecting blueberries and strawberries to make a pie. | What is his name? | ✅ `{"tokens":["bob"],"probability":0.8884454}` |

| ([link](https://localhost:5001/api/predict?Context=Bob%20is%20walking%20through%20the%20woods%20collecting%20blueberries%20and%20strawberries%20to%20make%20a%20pie.&Question=What%20will%20he%20bring%20home?)) | Bob is walking through the woods collecting blueberries and strawberries to make a pie. | What will he bring home? | ✅ `{"tokens":["blueberries","and","strawberries"],"probability":0.4070111}` |

| ([link](https://localhost:5001/api/predict?Context=Bob%20is%20walking%20through%20the%20woods%20collecting%20blueberries%20and%20strawberries%20to%20make%20a%20pie.&Question=Where%20is%20bob?)) | Bob is walking through the woods collecting blueberries and strawberries to make a pie. | Where is Bob? | ✅ `{"tokens":["walking","through","the","woods"],"probability":0.6123137}` |

| ([link](https://localhost:5001/api/predict?Context=Bob%20is%20walking%20through%20the%20woods%20collecting%20blueberries%20and%20strawberries%20to%20make%20a%20pie.&Question=What%20will%20he%20bake?)) | Bob is walking through the woods collecting blueberries and strawberries to make a pie. | What will he bake? | ❌ `{"tokens":["blueberries","and","strawberries"],"probability":0.48385787}` |