Training rasa model using GPU

Rasa Open Source
1

Hello all, I’m trying to train rasa model using GPU. my intent file have 60000 examples.

I want to know how should I train model using GPU. as I have never used GPU before. I would like to know how can I configure rasa to support gpu.

policies:
# No configuration for policies was provided. The following default policies were used to train your model.
# If you'd like to customize them, uncomment and adjust the policies.
# See https://rasa.com/docs/rasa/policies for more information.
  - name: MemoizationPolicy
  - name: RulePolicy
  - name: UnexpecTEDIntentPolicy
    max_history: 5
    epochs: 100
  - name: TEDPolicy
    max_history: 5
    epochs: 100
    constrain_similarities: true
  - name: DIETClassifier

Above are the policies I am using in my config.yml file

2

Assuming you are on an Intel system with Nvidia GPU, you would need to install the cuda driver. There are no changes to the config.yml.

When you run rasa train it prints out a message that tells you whether it sees the cuda driver and GPU.