Change Details

**Background** The ML team has decided to limit the experimental namespace to ml-staging in order to prevent non-production-ready model servers from being deployed to Lift Wing (production). We're currently drafting guidance on requirements for production-level models in T332711. The revert-risk language-agnostic model was properly tested in T321594. However, one thing is still missing before it can be deployed to production/API gateway: - [ ] Research team creates a model card for the model (e.g. [[ https://meta.wikimedia.org/wiki/Machine_learning_models/Production/Language_agnostic_link-based_article_topic_model_card | Language agnostic link-based article topic model card ]]) Once the model card is finished, to-dos for the ML team: - [ ] Create a "revert-risk" namespace to host the model and future models in the revert-risk family. - [ ] Deploy the model to production. - [ ] Enable the model in the API gateway. After the above tasks are completed, T330148 should be unblocked.

**Background** The ML team has decided to limit the experimental namespace to ml-staging in order to prevent non-production-ready model servers from being deployed to Lift Wing (production). We'll come up with guidance on requirements for production-level models in T332711. The revert-risk language-agnostic model was properly tested in T321594, but one thing is missing before it can be deployed to production/API gateway: - A model card (e.g. [[ https://meta.wikimedia.org/wiki/Machine_learning_models/Production/Language_agnostic_link-based_article_topic_model_card | Language agnostic link-based article topic model card ]]) Once the model card is finished, to-dos for the ML team: - Create a `revertrisk` generic namespace to host the model and future models in the revert-risk family. - Deploy the model to production. - Enable the model in the API gateway. After the above tasks are completed, T330148 should be unblocked.

**Background** The ML team has decided to limit the experimental namespace to ml-staging in order to prevent non-production-ready model servers from being deployed to Lift Wing (production). We're currently draftingWe'll come up with guidance on requirements for production-level models in T332711. The revert-risk language-agnostic model was properly tested in T321594. However, but one thing is stills missing before it can be deployed to production/API gateway: - [ ] Research team creates a- A model card for the model (erd (e.g. [[ https://meta.wikimedia.org/wiki/Machine_learning_models/Production/Language_agnostic_link-based_article_topic_model_card | Language agnostic link-based article topic model card ]]) Once the model card is finished, to-dos for the ML team: - [ ]- Create a "`revert-risk"` generic namespace to host the model and future models in the revert-risk family. - [ ] Deploy the model to production. - [ ] Enable the model in the API gateway. After the above tasks are completed, T330148 should be unblocked.