Skip to content

Commit

Permalink
feat: Add support for task type (CODE_RETRIEVAL_QUERY) through get_em…
Browse files Browse the repository at this point in the history
…beddings.

PiperOrigin-RevId: 686521364
  • Loading branch information
vertex-sdk-bot authored and copybara-github committed Oct 16, 2024
1 parent ae63a43 commit 7246497
Showing 1 changed file with 2 additions and 2 deletions.
4 changes: 2 additions & 2 deletions vertexai/language_models/_language_models.py
Original file line number Diff line number Diff line change
Expand Up @@ -267,7 +267,7 @@ def tune_model(
model_display_name: Custom display name for the tuned model.
tuning_evaluation_spec: Specification for the model evaluation during tuning.
default_context: The context to use for all training samples by default.
task_type: Type of task. Can be "RETRIEVAL_QUERY", "RETRIEVAL_DOCUMENT", "SEMANTIC_SIMILARITY", "CLASSIFICATION", "CLUSTERING", "QUESTION_ANSWERING", or "FACT_VERIFICATION".
task_type: Type of task. Can be "RETRIEVAL_QUERY", "RETRIEVAL_DOCUMENT", "SEMANTIC_SIMILARITY", "CLASSIFICATION", "CLUSTERING", "QUESTION_ANSWERING", "FACT_VERIFICATION", or "CODE_RETRIEVAL_QUERY".
machine_type: Machine type. E.g., "a2-highgpu-1g". See also: https://cloud.google.com/vertex-ai/docs/training/configure-compute.
accelerator: Kind of accelerator. E.g., "NVIDIA_TESLA_A100". See also: https://cloud.google.com/vertex-ai/docs/training/configure-compute.
accelerator_count: Count of accelerators.
Expand Down Expand Up @@ -2286,7 +2286,7 @@ def tune_model(
task_type: The task type expected to be used during inference.
Valid values are `DEFAULT`, `RETRIEVAL_QUERY`, `RETRIEVAL_DOCUMENT`,
`SEMANTIC_SIMILARITY`, `CLASSIFICATION`, `CLUSTERING`,
`FACT_VERIFICATION`, and `QUESTION_ANSWERING`.
`QUESTION_ANSWERING`, `FACT_VERIFICATION`, and `CODE_RETRIEVAL_QUERY`.
machine_type: The machine type to use for training. For information
about selecting the machine type that matches the accelerator
type and count you have selected, see
Expand Down

0 comments on commit 7246497

Please sign in to comment.