ChengpengLi

Results 6 issues of ChengpengLi

Hi, Could you please add a new baseline——MuggleMATH in the Comparing Arithmo-Mistral-7B with other LLM models section on the github webpage?MuggleMATH mainly investigates the scaling law and generalization for data...

Hello, Thanks for your open sources. However, I cannot find the training data of GSM8K, could you please help me with it ?

Hi, Could you please add a new baseline——MuggleMATH in the Leaderboard for Mathematical Reasoning on the github webpage? MuggleMATH mainly investigates the scaling law and generalization for data augmentation for...

Please consider add Paper: Long CoT with tool(code Interpreter): 1. START: Self-taught Reasoner with Tools (https://arxiv.org/abs/2503.04625) 2. CoRT: Code-integrated Reasoning within Thinking (https://arxiv.org/abs/2506.09820) Code Base: RL framework for longCoT with...