leaked prompts of GPTs

✨✨Latest Papers and Benchmarks in Reasoning with Foundation Models

Best practice for training transformer models in Megatron-LM

中国大模型

Resource, Evaluation and Detection Papers for ChatGPT

Repository of DISC-MedLLM, it is a comprehensive solution that leverages Large Language Models (LLMs) to provide accurate and truthful medical response in end-to-end conversational healthcare servi…

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark

👾 Open source implementation of the ChatGPT Code Interpreter

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO。

Medical NLP Competition, dataset, large models, paper

Large-scale, Informative, and Diverse Multi-round Chat Data (and Models)

明医 (MING)：中文医疗问诊大模型

This is updated version of the dataset for Chinese community medical question answering.

总结Prompt&LLM论文，开源数据&模型，AIGC应用

Linux virtual machines, with a focus on running containers

Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

A large-scale 7B pretraining language model developed by BaiChuan-Inc.

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Dromedary: towards helpful, ethical and reliable LLMs.

GAOKAO-Bench is an evaluation framework that utilizes GAOKAO questions as a dataset to evaluate large language models.

SuperCLUE: 中文通用大模型综合性基准 | A Benchmark for Foundation Models in Chinese

Panda项目是于2023年5月启动的开源海外中文大语言模型项目，致力于大模型时代探索整个技术栈，旨在推动中文自然语言处理领域的创新和合作。

Benchmarking large language models' complex reasoning ability with chain-of-thought prompting

OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset