An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

[ACL 2024 Findings] MathBench: A Comprehensive Multi-Level Difficulty Mathematics Evaluation Dataset

Code for the paper "Language Models are Unsupervised Multitask Learners"

哈尔滨工业大学（深圳）计算机专业课程攻略 | Guidance for courses in Department of Computer Science, Harbin Institute of Technology (Shenzhen)

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.