microsoft

/

biogpt

like 221

Could you clarify? You can get embeddings from this model directly using the AutoModel API.

If you want to get sentence embbedings from the model you can use the snippet in this link. Just replace the model name with "microsoft/biogpt".

Hello , are we able take a model trained for text generation(BioGPT) and use it to produce embeddings that make sense, without further training? Are these generated embeddings can be used and have a meaning?

I tried to use biogpt to generate embeddings and perform similarity to find matches but its accuracy is very low as compare to models trained on self-alignment task for biomedical entities. I used this model to generate embeddings like any model using sentence transform code. Can we use this model for embedding at all? Can someone shed light if they managed to use it?