Tutorial on training, evaluating LLM, as well as utilizing RAG, Agent, Chain to build entertaining applications with LLMs.分享如何训练、评估LLMs，如何基于RAG、Agent、Chain构建有趣的LLMs应用。

雅意信息抽取大模型：在百万级人工构造的高质量信息抽取数据上进行指令微调，由中科闻歌算法团队研发。 (Repo for YAYI Unified Information Extraction Model)

Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).

一个基于HuggingFace开发的大语言模型训练、测试工具。支持各模型的webui、终端预测，低参数量及全参数模型训练(预训练、SFT、RM、PPO、DPO)和融合、量化。

Scripts of LLM pre-training and fine-tuning (w/wo LoRA, DeepSpeed)

[ACL 2024] Can Watermarks Survive Translation? On the Cross-lingual Consistency of Text Watermark for Large Language Models

to train a wechat version of yourself. 用微信聊天数据训练微信版的你, aka wechat-me. 支持Qwen1.5, Yi, InterLM2, ChatGLM3, Baichuan2等。

基于星火大模型的博物百科小程序

(简单/Simple 易学/Hackable 的中文大模型微调) lit-gpt with chinese models, Qwen1.5/MoE, InternLM2, Yi, Baichuan2, ChatGLM2/3.

使用Python, requests，用于快速将百川智能大语言模型接入项目

lit-gpt for chinese

Programming Language for Deep Learning in Python