Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting…

PyTorch native finetuning library

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Curate better data for LLMs

An Open-Ended Embodied Agent with Large Language Models

leaked prompts of GPTs

A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).

Code base for internal reward models and PPO training

Tools for merging pretrained large language models.

LlamaIndex is a data framework for your LLM applications

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and…

FaceChain is a deep-learning toolchain for generating your Digital-Twin.

Unofficial implementation of AlpaGasus

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/

Official codes for ACL 2023 paper "WebCPM: Interactive Web Search for Chinese Long-form Question Answering"

Python ProxyPool for web spider

LLM(😽)

搜索所有中文NLP数据集，附常用英文NLP数据集

Chat凉宫春日, An open sourced Role-Playing chatbot Cheng Li, Ziang Leng, and others.

Giving the power of LLM's to a MUD lib.

Customizable implementation of the self-instruct paper.

Dromedary: towards helpful, ethical and reliable LLMs.

pCLUE: 1000000+多任务提示学习数据集

Chinese Couplets Dataset without vulgar words. 不包含敏感内容的对联数据集。

MNBVC(Massive Never-ending BT Vast Chinese corpus)超大规模中文语料集。对标chatGPT训练的40T数据。MNBVC数据集不但包括主流文化，也包括各个小众文化甚至火星文的数据。MNBVC数据集包括新闻、作文、小说、书籍、杂志、论文、台词、帖子、wiki、古诗、歌词、商品介绍、笑话、糗事、聊天记录等一切形式的纯文本中文数据。

Open Academic Research on Improving LLaMA to SOTA LLM