Commit
·
3d308b0
1
Parent(s):
358bd44
Typo in README fixed. (#1)
Browse files- Typo in README fixed. (d7cb280f92678aa9e1d244e5ec1059d09758f21c)
Co-authored-by: Neeraj Cherakara <[email protected]>
README.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
license: mit
|
| 3 |
---
|
| 4 |
|
| 5 |
-
This model is a
|
| 6 |
|
| 7 |
Self-RAG is trained on our instruction-following corpora with interleaving passages and reflection tokens using the standard next-token prediction objective, enabling efficient and stable learning with fine-grained feedback.
|
| 8 |
At inference, we leverage reflection tokens covering diverse aspects of generations to sample the best output aligning users' preferences.
|
|
|
|
| 2 |
license: mit
|
| 3 |
---
|
| 4 |
|
| 5 |
+
This model is a 13B [Self-RAG](https://selfrag.github.io/) model that generates outputs to diverse user queries as well as *reflection tokens* to call the retrieval system adaptively and criticize its own output and retrieved passages.
|
| 6 |
|
| 7 |
Self-RAG is trained on our instruction-following corpora with interleaving passages and reflection tokens using the standard next-token prediction objective, enabling efficient and stable learning with fine-grained feedback.
|
| 8 |
At inference, we leverage reflection tokens covering diverse aspects of generations to sample the best output aligning users' preferences.
|