Sponsored by
Qoder
baidu / Themis-7b
Model's Last Updated: March 10 2024
Introduction of Themis-7b
Model Details of Themis-7b
Offical checkpoint for Tool-Augmented Reward Modeling (ICLR 2024 spotlight) .
Model Description
Themis is a tool-augmented preference model to address these limitations by empowering RMs with access to external environments, including calculators and search engines. It was introduced in the ICLR 2024 paper and first released in this repository . Themis-7b is trained with TARA , achieving a noteworthy overall improvement of 17.7% across eight tasks in preference ranking.
🔥 News
-
9 February, 2024:
🎉 We release the official codebase and model weights of
baidu/Themis-7b. Stay tuned!🔥 - 16 January, 2024: 🎉 Our work has been accepted to ICLR 2024 spotlight ! ✨
Citation
@inproceedings{tarm-2024-ernie,
author = {Lei Li and
Yekun Chai and
Shuohuan Wang and
Yu Sun and
Hao Tian and
Ningyu Zhang and
Hua Wu},
title = {Tool-Augmented Reward Modeling},
booktitle = {The Twelfth International Conference on Learning Representations (ICLR)},
year = {2024},
url = {https://openreview.net/forum?id=d94x0gWTUX},
}
Runs of baidu Themis-7b on huggingface.co
1
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs
More Information About Themis-7b huggingface.co Model
Url of Themis-7b
Themis-7b huggingface.co Url
Provider of Themis-7b huggingface.co
Other API from baidu
Total runs:
95.9K
Run Growth:
-116.0K
Growth Rate:
-109.18%
Total runs:
33.2K
Run Growth:
-17.6K
Growth Rate:
-51.06%
Total runs:
16.7K
Run Growth:
2.5K
Growth Rate:
14.46%
Total runs:
3.1K
Run Growth:
2.3K
Growth Rate:
76.49%
Total runs:
2.2K
Run Growth:
590
Growth Rate:
26.76%
Total runs:
2.1K
Run Growth:
-714
Growth Rate:
-33.47%
Total runs:
346
Run Growth:
-511
Growth Rate:
-142.74%
Total runs:
313
Run Growth:
94
Growth Rate:
28.06%
Total runs:
298
Run Growth:
-568
Growth Rate:
-116.39%
Total runs:
241
Run Growth:
3
Growth Rate:
1.12%
Total runs:
218
Run Growth:
44
Growth Rate:
20.95%
Total runs:
144
Run Growth:
74
Growth Rate:
50.68%
Total runs:
62
Run Growth:
17
Growth Rate:
27.42%
Total runs:
56
Run Growth:
-29
Growth Rate:
-50.88%
Total runs:
50
Run Growth:
10
Growth Rate:
19.61%
Total runs:
50
Run Growth:
-23
Growth Rate:
-47.92%
Total runs:
49
Run Growth:
-1
Growth Rate:
-2.00%
Total runs:
47
Run Growth:
15
Growth Rate:
31.25%
Total runs:
44
Run Growth:
7
Growth Rate:
15.56%
Total runs:
43
Run Growth:
6
Growth Rate:
13.64%
Total runs:
40
Run Growth:
-17
Growth Rate:
-40.48%
Total runs:
38
Run Growth:
-24
Growth Rate:
-66.67%
Total runs:
36
Run Growth:
-52
Growth Rate:
-152.94%
Total runs:
33
Run Growth:
0
Growth Rate:
0.00%
Total runs:
32
Run Growth:
1
Growth Rate:
3.03%
Total runs:
31
Run Growth:
-19
Growth Rate:
-57.58%
Total runs:
3
Run Growth:
0
Growth Rate:
0.00%
Total runs:
2
Run Growth:
0
Growth Rate:
0.00%
Total runs:
2
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%