feat: finetuning via ST
#42
by
jupyterjazz
- opened
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
lgtm!
jupyterjazz
changed pull request status to
merged