Jina AI org
edited Oct 10

These changes allow fine-tuning v3 via SentenceTransformers

make sure to specify which adapter/task you want to fine-tune either during model loading or afterwards:

model = SentenceTransformer("jinaai/jina-embeddings-v3", trust_remote_code=True, model_kwargs={'default_task': 'classification'})

or

model = SentenceTransformer("jinaai/jina-embeddings-v3", trust_remote_code=True)
model[0].default_task = 'classification'
jupyterjazz changed pull request title from feat: support setting a default task to feat: finetuning via ST
Jina AI org

lgtm!

jupyterjazz changed pull request status to merged

Sign up or log in to comment