When using LanguageModelFeaturizer to load a pre-trained model during rasa train nlu, an error is reported: "Error initializing graph component for node run_LanguageModelFeaturizer1."

Rasa Open Source
1

When using LanguageModelFeaturizer to load a pre-trained model during rasa train nlu, an error is reported: “Error initializing graph component for node run_LanguageModelFeaturizer1.”

TypeError: stat: path should be string, bytes, os.PathLike or integer, not NoneType rasa.engine.exceptions.GraphComponentException: Error initializing graph component for node run_LanguageModelFeaturizer1.

rasa:3.6 windows

config.yaml recipe: default.v1

language: zh

pipeline:

  • name: JiebaTokenizer

  • name: LanguageModelFeaturizer model_name: “bert” model_weights: “bert-base-chinese”

  • name: “DIETClassifier” epochs: 100

policies: null assistant_id: 20230618-210312-overcast-quetzal

# 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 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