Loading embedding model form Hugging Face in Llama Index throws up an...

spark_sara

I am trying to load embeddings like this.I changed the code to reflect the current version change in LlamaIndex but it shows up an attribute error. from llama_index.embeddings.huggingface import HuggingFaceEmbedding from llama_index.core import Settings Settings.embed_model = HuggingFaceEmbedding( model_name="BAAI/bge-small-en-v1.5" ) AttributeError: module 'torch._subclasses' has no attribute 'functional_tensor' The above exception was the...

Originally asked by Rahul_51 on Stack Exchange (stackoverflow) (CC BY-SA 4.0).

uphilltech

Great question — answering as the UphillTech team:

Check for your torch version !python -c "import torch; print(torch. version )" Downgrading it works !python -m pip install --upgrade torch==1.13.0

Full answer by Rahul_51: https://stackoverflow.stackexchange.com/a/78025072 (CC BY-SA 4.0).

Need it done for your business? UphillTech.