Usage in llamaindex
#12
by
TungThanh94
- opened
Hello.
I'm using this in my llamaindex project. This is my code to load the model.
from llama_index.core import Settings
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
Settings.embed_model = HuggingFaceEmbedding(model_name=embed_name_or_path)
In the terminal, I see this warning:
"Some weights of BertModel were not initialized from the model checkpoint at Snowflake/snowflake-arctic-embed-m and are newly initialized: ['pooler.dense.bias', 'pooler.dense.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference."
Can anyone help me on how to load the model correctly.
Thanks a lot!
I have followed up with the llama index folks, who have updated their config not to include poolers. This should be fixed.
Fixed
spacemanidol
changed discussion status to
closed