Open jcuenod opened 1 year ago
Hi @jcuenod simalign mainly supports encoder-only models (like mBERT, XLM-R). Seems that for this model you would need to specify e.g., decoder_input_ids. A quick solution could be to feed sentence A to the encoder and sentence B to the decoder and then apply simalign to the similarity matrix. Feel free to create a PR to add this capability.
Thanks, I'll take a look at submitting a PR.
I tried using Meta's
facebook/nllb-200-distilled-600M
model, but it seems thathidden_states
is not being set on theself.emb_model
output (line 65). I'm getting:Any suggestions for how to use NLLB?