(404 Not Found) for url (https://huggingface.co/BAAI/bge-reranker-v2-gemma/resolve/main/pytorch_model.bin)
#4
by qwerasdfzxv - opened
To reproduce:
docker run -p 8080:80 ghcr.io/huggingface/text-embeddings-inference:cpu-1.2 --model-id=BAAI/bge-reranker-v2-gemma
The model is saved in safetensors format, so there is no pytorch_model.bin
Thanks for the reply.
Switching to ghcr.io/huggingface/text-embeddings-inference:cpu-latest solves it. Looks like they just added the support for model.safetensors.index.json in https://github.com/huggingface/text-embeddings-inference/commit/7c9b7cb251858b84bbcb7d4abc476ffa2c42b0d9