sauc-abadal-lloret
/

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

Model card Files Files and versions Community

sauc-abadal-lloret commited on Sep 25

Commit

e2d0d1e

•

1 Parent(s): e636989

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -29,7 +29,7 @@ In particular, the **ALT-RM** checkpoint collects the feedback by leveraging a [
 ```
 Thus, at inference time, the expected aligned behavior can be attained by conditioning the input with the *'Excellent.'* feedback.
-**Related Models:** [ALT-Quark]().
 # Intended uses & limitations
 This model originates from a research project focused on alignment and is intended primarily for research purposes. Commercial use as an off-the-shelf model is discouraged, as it was not designed with such applications in mind. The model is tailored specifically for the summarization task, having been trained on the TL;DR dataset, though some out-of-distribution generalization may be possible for related datasets.

 ```
 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).
 # Intended uses & limitations
 This model originates from a research project focused on alignment and is intended primarily for research purposes. Commercial use as an off-the-shelf model is discouraged, as it was not designed with such applications in mind. The model is tailored specifically for the summarization task, having been trained on the TL;DR dataset, though some out-of-distribution generalization may be possible for related datasets.