Update README.md

README.md

@@ -7,30 +7,19 @@ sdk: static
 pinned: false
 ---
 
----
-title: README
-emoji: 🚀
-colorFrom: blue
-colorTo: gray
-sdk: static
-pinned: true
----
 
-# 🐙 Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations
+# 🪄 GraphWiz: An Instruction-Following Language Model for Graph Problems
 
 Project Page: [https://mathoctopus.github.io/](https://mathoctopus.github.io/)
 
 Paper: [https://arxiv.org/abs/2310.20246.pdf](https://arxiv.org/abs/2310.20246.pdf)
 
-Code: [https://github.com/microsoft/MathOctopus](https://github.com/microsoft/MathOctopus)
+Code: [https://github.com/nuochenpku/Graph-Reasoning-LLM](https://github.com/nuochenpku/Graph-Reasoning-LLM)
 
 ## About Mathoctopus
+This  project aims at leveraging instruction-tuning to build a powerful instruction-following LLM that can map textural descriptions of graphs and structures, and then solve different graph problems explicitly in natural language.
 
-Mathoctopus is a series of multilingual math reasoning large language models based on LLaMA.
-
-This work pioneers exploring and building powerful  Multilingual Math Reasoning (xMR) LLMs. To accomplish this, we make the following works:
-
-- **MGSM8KInstruct**,  the  multilingual math reasoning instruction dataset,  encompassing ten distinct languages, thus addressing the issue of training data scarcity in xMR tasks.
-- **MSVAMP**, an out-of-domain xMR test dataset, to conduct a more exhaustive and comprehensive evaluation of the model’s multilingual mathematical capabilities.
-- **MathOctopus**, our effective Multilingual Math Reasoning  LLMs,  training with  different strategies, which notably outperform conventional open-source LLMs and exhibit superiority over ChatGPT in few-shot scenarios.
-
+- **GraphWiz**, a series of instruction-following LLMs that have strong  graph problem-solving abilities and output explicit reasoning paths.
+- **GraphInstruct**, which offers over 72.5k training samples across nine graph problem
+tasks, ranging in complexity from linear and polynomial to NP-complete, extending the scope, scale,
+and diversity of previous benchmarks.