sauc-abadal-lloret
/

gpt-j-6b-ALT-RM-tldr

Model card Files Files and versions Community

sauc-abadal-lloret commited on Sep 25

Commit

cd943c7

•

1 Parent(s): e2d0d1e

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -27,7 +27,7 @@ In particular, the **ALT-RM** checkpoint collects the feedback by leveraging a [
  'QUANTILE 3': 'Bad.',
  'QUANTILE 4': 'Horrible.'}
 ```
-Thus, at inference time, the expected aligned behavior can be attained by conditioning the input with the *'Excellent.'* feedback.
 **Related Models:** [ALT-Quark](https://huggingface.co/sauc-abadal-lloret/gpt-j-6b-ALT-Quark-tldr).

  'QUANTILE 3': 'Bad.',
  'QUANTILE 4': 'Horrible.'}
 ```
+Thus, at inference time, the expected aligned behavior can be attained by conditioning the input with the `Excellent.` feedback.
 **Related Models:** [ALT-Quark](https://huggingface.co/sauc-abadal-lloret/gpt-j-6b-ALT-Quark-tldr).