Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,29 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- gair-prox/open-web-math-pro
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
tags:
|
| 8 |
+
- math
|
| 9 |
+
- reasoning
|
| 10 |
+
---
|
| 11 |
+
<img src="prox.png" width="400">
|
| 12 |
+
|
| 13 |
+
[ArXiv](http://arxiv.org/abs/xxxx) | [Models](https://huggingface.co/gair-prox/ProX-RedPJ-0.3B) | [Data](https://huggingface.co/datasets/gair-prox/RedPajama-pro) | [Code](https://github.com/GAIR-NLP/program-every-example)
|
| 14 |
+
|
| 15 |
+
**ProX-RedPJ-0.3B** is a tiny language model. It was and trained on the [RedPajama-V2-pro](https://huggingface.co/datasets/gair-prox/RedPajama-pro) for 25B tokens.
|
| 16 |
+
|
| 17 |
+
## Evaluations
|
| 18 |
+
|
| 19 |
+
ProX models are evaluated over 10 language model benchmarks in zero-shot setting.
|
| 20 |
+
|
| 21 |
+
| ARC-C | ARC-E | CSQA | HellaSwag | MMLU | OBQA | PiQA | SIQA | WinoG | SciQ | AVG |
|
| 22 |
+
|--------|--------|--------|-----------|--------|--------|--------|--------|--------|--------|------|
|
| 23 |
+
| 25.90 | 47.50 | 29.20 | 36.70 | 28.11 | 30.20 | 64.60 | 38.00 | 51.70 | 71.40 | 42.3 |
|
| 24 |
+
|
| 25 |
+
### Citation
|
| 26 |
+
```
|
| 27 |
+
@misc{TBD
|
| 28 |
+
}
|
| 29 |
+
```
|