Can I deploy rerank model with TEI in an offline environment? #389
Unanswered
kennard520
asked this question in
Q&A
Replies: 1 comment 1 reply
-
You need an internet connection to download the model for the first time from HuggingFace. Afterwards you can run it locally and offline. |
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Below is my command:
docker run --gpus all -p 8081:80 -v /root/^Cta:/data 192.168.0.140:8082/ghcr.io/huggingface/text-embeddings-inference:1.5 --model-id BAAI/bge-reranker-v2-m3 --tokenization-workers=5 --max-concurrent-requests=10 --max-batch-tokens=8192 --max-batch-requests=10 --pooling=mean
but always download config
2024-08-26T01:02:32.430578Z INFO download_new_st_config: text_embeddings_core::download: core/src/download.rs:62: Downloading
config_sentence_transformers.json``Can I deploy in an offine env?
Beta Was this translation helpful? Give feedback.
All reactions