YandexGPT API models
YandexGPT API provides access to large generative models:
- Standard YandexGPT Lite suitable for solving tasks in real time.
- Large YandexGPT Pro based on YandexGPT 3 that provides more accurate responses to complex prompts.
- Special summary model based on YandexGPT Lite.
- YandexGPT Lite RC model based on YandexGPT 3 available in Release Candidate status.
If out-of-the-box models are not enough, you can fine-tune YandexGPT Pro in Yandex DataSphere
To access your model via the API, under modelUri
, specify its URI/latest
segment specifies the model version and is optional.
YandexGPT API generation models
Model | YandexGPT generation | URI | Operation mode |
---|---|---|---|
YandexGPT Pro | 3 | gpt://<folder_ID>/yandexgpt/latest |
Asynchronous, synchronous |
YandexGPT Lite | 2 | gpt://<folder_ID>/yandexgpt-lite/latest |
Asynchronous, synchronous |
YandexGPT Lite RC | 3 | gpt://<folder_ID>/yandexgpt-lite/rc |
Asynchronous, synchronous |
Summary | 2 | gpt://<folder_ID>/summarization/latest |
Asynchronous, synchronous |
Model fine-tuned in Yandex DataSphere | 3 | ds://<fine_tuned_model_ID> |
Asynchronous, synchronous |
Modified models share usage quotas with their basic models.
Fine-tuning capabilities
You cannot tune the YandexGPT Pro model on new information, e.g., a support service knowledge base. However, you can train the model to generate responses in a specific format or analyze texts. You can train the model to:
- Summarize and rewrite texts.
- Generate questions and answers from text input.
- Provide responses in a particular format or style.
- Classify texts, forms of address, and dialogs.
- Extract data from texts.
If you want to fine-tune the model for other capabilities, contact our support team
Note
To make sure a tuned model works properly, specify the prompt used during training in the message with the sender role set as system
.