nicholasKluge
/

RewardModel

Text Classification

preference model

text-embeddings-inference

Model card Files Files and versions

nicholasKluge commited on Jun 13, 2023

Commit

a5a97d2

·

1 Parent(s): e59dd6d

Update README.md

Files changed (1) hide show

README.md +3 -0

README.md CHANGED Viewed

@@ -96,6 +96,9 @@ tokens_bad = tokenizer(prompt, response_bad,
                 return_tensors="pt",
                 return_attention_mask=True)
 score_good = rewardModel(**tokens_good)[0].item()
 score_bad = rewardModel(**tokens_bad)[0].item()

                 return_tensors="pt",
                 return_attention_mask=True)
+tokens_good.to(device)
+tokens_bad.to(device)
 score_good = rewardModel(**tokens_good)[0].item()
 score_bad = rewardModel(**tokens_bad)[0].item()