Trains and deploys a fine-tuned model.

from cohere.finetuning import (
    BaseModel,
    FinetunedModel,
    Hyperparameters,
    Settings,
    WandbConfig,
)
import cohere
co = cohere.Client()
hp = Hyperparameters(
    early_stopping_patience=10,
    early_stopping_threshold=0.001,
    train_batch_size=16,
    train_epochs=1,
    learning_rate=0.01,
)
wnb_config = WandbConfig(
    project="test-project",
    api_key="<<wandbApiKey>>",
    entity="test-entity",
)
finetuned_model = co.finetuning.create_finetuned_model(
    request=FinetunedModel(
        name="test-finetuned-model",
        settings=Settings(
            base_model=BaseModel(
                base_type="BASE_TYPE_CHAT",
            ),
            dataset_id="my-dataset-id",
            hyperparameters=hp,
            wandb=wnb_config,
        ),
    )
)
print(finetuned_model)

{
  "finetuned_model": {
    "name": "customer-support-chatbot-v1",
    "settings": {
      "base_model": {
        "base_type": "BASE_TYPE_CHAT",
        "name": "cohere-chat-2024",
        "version": "v2.1.0",
        "strategy": "STRATEGY_VANILLA"
      },
      "dataset_id": "customer-support-dataset-2024",
      "hyperparameters": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0005,
        "train_batch_size": 32,
        "train_epochs": 3,
        "learning_rate": 0.005,
        "lora_alpha": 16,
        "lora_rank": 4,
        "lora_target_modules": "LORA_TARGET_MODULES_QKVO"
      },
      "multi_label": false,
      "wandb": {
        "project": "customer-support-finetuning",
        "api_key": "wandb_api_key_1234567890abcdef",
        "entity": "cohere-team"
      }
    },
    "id": "ftm_123e4567-e89b-12d3-a456-426614174000",
    "creator_id": "user_789a1234-b56c-78d9-e012-3456789abcde",
    "organization_id": "org_456b7890-c12d-34e5-f678-901234567890",
    "status": "STATUS_FINETUNING",
    "created_at": "2024-01-15T09:30:00Z",
    "updated_at": "2024-01-20T14:45:00Z",
    "completed_at": "2024-01-25T18:00:00Z",
    "last_used": "2024-02-01T12:00:00Z"
  }
}

Creates a new fine-tuned model. The model will be trained on the dataset specified in the request body. The training process may take some time, and the model will be available once the training is complete.

Authentication

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

Request

Information about the fine-tuned model. Must contain name and settings.

namestringRequired

FinetunedModel name (e.g. foobar).

settingsobjectRequired

FinetunedModel settings such as dataset, hyperparameters...

statusenumOptionalDefaults to STATUS_UNSPECIFIED

read-only. Current stage in the life-cycle of the fine-tuned model.

Response

A successful response.

finetuned_modelobject

Information about the fine-tuned model.

Errors

400

Bad Request Error

401

Unauthorized Error

403

Forbidden Error

404

Not Found Error

500

Internal Server Error

503

Service Unavailable Error

Authentication

Headers

Request

Response

Errors