Update README.md
Browse files
README.md
CHANGED
|
@@ -18,9 +18,7 @@ Rho-1: Not All Tokens Are What You Need
|
|
| 18 |
<a href="https://arxiv.org/abs/2404.07965"><b>[📜 Arxiv]</b></a> •
|
| 19 |
<a href="https://huggingface.co/papers/2404.07965"><b>[💬 HF Paper]</b></a> •
|
| 20 |
<a href="https://huggingface.co/microsoft/rho-math-1b-v0.1"><b>[🤗 Models]</b></a> •
|
| 21 |
-
<a href="https://github.com/microsoft/rho"><b>[🐱 GitHub]</b></a>
|
| 22 |
-
<a href="https://twitter.com/zebgou/status/1778676535404396697"><b>[🐦 Twitter]</b></a> •
|
| 23 |
-
<a href="https://huggingface.co/spaces/zubingou/rho-1"><b>[🤖 Gradio Demo]</b></a>
|
| 24 |
</p>
|
| 25 |
|
| 26 |
<p align="center">
|
|
@@ -32,7 +30,6 @@ Rho-1: Not All Tokens Are What You Need
|
|
| 32 |
|
| 33 |
## 🔥 News
|
| 34 |
|
| 35 |
-
- [2024/04/14] 🚀🚀🚀 We release [Gradio demo of Rho-1 Code Interpreter](https://huggingface.co/spaces/zubingou/rho-1), try it out!
|
| 36 |
- [2024/04/12] 🔥🔥🔥 Rho-Math-v0.1 models released at 🤗 HuggingFace!
|
| 37 |
- [Rho-Math-1B](https://huggingface.co/microsoft/rho-math-1b-v0.1) and [Rho-Math-7B](https://huggingface.co/microsoft/rho-math-7b-v0.1) achieve 15.6% and 31.0% few-shot accuracy on MATH dataset, respectively — matching DeepSeekMath with only 3\% of the pretraining tokens.
|
| 38 |
- [Rho-Math-1B-Interpreter](https://huggingface.co/microsoft/rho-math-1b-interpreter-v0.1) is the first 1B LLM that achieves over 40% accuracy on MATH.
|
|
|
|
| 18 |
<a href="https://arxiv.org/abs/2404.07965"><b>[📜 Arxiv]</b></a> •
|
| 19 |
<a href="https://huggingface.co/papers/2404.07965"><b>[💬 HF Paper]</b></a> •
|
| 20 |
<a href="https://huggingface.co/microsoft/rho-math-1b-v0.1"><b>[🤗 Models]</b></a> •
|
| 21 |
+
<a href="https://github.com/microsoft/rho"><b>[🐱 GitHub]</b></a>
|
|
|
|
|
|
|
| 22 |
</p>
|
| 23 |
|
| 24 |
<p align="center">
|
|
|
|
| 30 |
|
| 31 |
## 🔥 News
|
| 32 |
|
|
|
|
| 33 |
- [2024/04/12] 🔥🔥🔥 Rho-Math-v0.1 models released at 🤗 HuggingFace!
|
| 34 |
- [Rho-Math-1B](https://huggingface.co/microsoft/rho-math-1b-v0.1) and [Rho-Math-7B](https://huggingface.co/microsoft/rho-math-7b-v0.1) achieve 15.6% and 31.0% few-shot accuracy on MATH dataset, respectively — matching DeepSeekMath with only 3\% of the pretraining tokens.
|
| 35 |
- [Rho-Math-1B-Interpreter](https://huggingface.co/microsoft/rho-math-1b-interpreter-v0.1) is the first 1B LLM that achieves over 40% accuracy on MATH.
|