McGill-NLP
/

LLM2Vec-Mistral-7B-Instruct-v2-mntp-unsup-simcse

Model card Files Files and versions Community

vaibhavad commited on Apr 5

Commit

e0359e8

•

1 Parent(s): 6376430

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -66,7 +66,7 @@ model = model.merge_and_unload()  # This can take several minutes on cpu
 # Loading unsupervised SimCSE model. This loads the trained LoRA weights on top of MNTP model. Hence the final weights are -- Base model + MNTP (LoRA) + SimCSE (LoRA).
 model = PeftModel.from_pretrained(
-    model, "McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-unsup-simcse"
 )
 # Wrapper for encoding and pooling operations

 # Loading unsupervised SimCSE model. This loads the trained LoRA weights on top of MNTP model. Hence the final weights are -- Base model + MNTP (LoRA) + SimCSE (LoRA).
 model = PeftModel.from_pretrained(
+    model, "McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-unsup-simcse"
 )
 # Wrapper for encoding and pooling operations