A central, open resource for data and tools related to chain-of-thought reasoning in large language models. Developed @ Samwald research group: https://samwald.info/

Evaluate the accuracy of LLM generated outputs

追一科技首届中文NL2SQL挑战赛决赛第3名方案+代码

Code and data for "MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning" [ICLR 2024]

Readable implementation of a Capsule Network as described in "Dynamic Routing Between Capsules" [Hinton et. al.]

This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.

Code for the curation of The Stack v2 and StarCoder2 training data

Distributional Generalization in NLP. A roadmap.

A system for CCKS2019-CKBQA, whose single system reach 0.69 and ensemble system reach 0.73