Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,8 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Paper: https://arxiv.org/abs/2308.15812
|
| 2 |
+
|
| 3 |
+
Setup: https://github.com/Hritikbansal/sparse_feedback/tree/main#reward-modeling
|
| 4 |
+
|
| 5 |
+
|
| 6 |
+
Example Usage: https://github.com/Hritikbansal/sparse_feedback/blob/main/inference/reranking.py
|
| 7 |
+
Download the checkpoints and provide their path as "reward_model_path"
|
| 8 |
+
"alpaca_model_path": Path to alpaca-7b checkpoint
|