databricks/lilac

Clustering Error: Trying to Access Jina

arnicas opened this issue · 1 comments

I don't know why it wants to use Jina, I started with gte-small as my preferred, and then in the UI (after initial error) changed to sbert, but got this error repeatedly:

`Uvicorn running on http://127.0.0.1:5432 (Press CTRL+C to quit)
Dataset "drinks" written to /home/lcherny/lilac-wines/datasets/local/drinks
[local/drinks][1 shards] map "extract_text" to "('drink__cluster',)": 100%|█| 3792/3792 [00:00<00:00, 37010.72it/s
Wrote map output to drink__cluster-00000-of-00001.parquet
[local/drinks][1 shards] map "cluster_documents" to "('drink__cluster',)": 0%| | 0/3792 [00:00<?, ?it/s]Computing embeddings took 12.783s.
[local/drinks][1 shards] map "cluster_documents" to "('drink__cluster',)": 0%| | 0/3792 [00:12<?, ?it/s]
You are trying to access a gated repo.
Make sure to have access to it at https://huggingface.co/jinaai/jina-embeddings-v2-small-en.
401 Client Error. (Request ID: Root=1-65f0575b-6899db663d39ae18736f3af1;1d66f581-7d6e-4f58-9c05-e4855bf3aee6)

Cannot access gated repo for url https://huggingface.co/jinaai/jina-embeddings-v2-small-en/resolve/main/config.json.
Repo model jinaai/jina-embeddings-v2-small-en is gated. You must be authenticated to access it.
[local/drinks][1 shards] map "extract_text" to "('drink__cluster',)": 100%|█| 3792/3792 [00:00<00:00, 35773.20it/s
Wrote map output to drink__cluster-00000-of-00001.parquet
[local/drinks][1 shards] map "cluster_documents" to "('drink__cluster',)": 0%| | 0/3792 [00:00<?, ?it/s]Computing embeddings took 0.271s.
[local/drinks][1 shards] map "cluster_documents" to "('drink__cluster',)": 0%| | 0/3792 [00:00<?, ?it/s]
You are trying to access a gated repo.
Make sure to have access to it at https://huggingface.co/jinaai/jina-embeddings-v2-small-en.
401 Client Error. (Request ID: Root=1-65f057ad-79c4fbda2b603808501015c4;d199ef06-a06c-4480-8e69-18f9eb353c36)

Cannot access gated repo for url https://huggingface.co/jinaai/jina-embeddings-v2-small-en/resolve/main/config.json.
Repo model jinaai/jina-embeddings-v2-small-en is gated. You must be authenticated to access it.`