Commit
•
cabb2d4
1
Parent(s):
34ef40b
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,18 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- nlp
|
| 5 |
+
- math
|
| 6 |
+
language:
|
| 7 |
+
- en
|
| 8 |
+
pipeline_tag: text-generation
|
| 9 |
---
|
| 10 |
+
|
| 11 |
+
## Rho-1: Not All Tokens Are What You Need
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
The Rho-1 series are pretrained language models that utilize Selective Language Modeling (SLM) objectives.
|
| 15 |
+
In math reasoning pretraining, SLM improves average few-shot accuracy on GSM8k and MATH by over 16%, achieving the baseline performance 5-10x faster.
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
For more details please check our [github](https://github.com/microsoft/rho).
|