这是一个从头训练大语言模型的项目，包括预训练、微调和直接偏好优化，模型拥有1B参数，支持中英文。

LLM finetuning for Sudoku solving

新词发现 基于词频、凝聚系数和左右邻接信息熵

📚A curated list of Awesome LLM/VLM Inference Papers with codes: WINT8/4, FlashAttention, PagedAttention, Parallelism, MLA, etc.

[NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filli…

SGLang is a fast serving framework for large language models and vision language models.

[ICML'2024] Can AI Assistants Know What They Don't Know?

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。

The official GitHub page for the survey paper "A Survey of Large Language Models".

Curated tutorials and resources for Large Language Models, Text2SQL, Text2DSL、Text2API、Text2Vis and more.

NL2SQL competition dataset

Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

General technology for enabling AI capabilities w/ LLMs and MLLMs

Code and models for ICML 2024 paper, NExT-GPT: Any-to-Any Multimodal Large Language Model

🦜🔗 Build context-aware reasoning applications

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

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

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

A (somewhat) minimal library for finetuning language models with PPO on human feedback.

Llama中文社区，实时汇总最新Llama学习资料，构建最好的中文Llama大模型开源生态，完全开源可商用

对ChatGLM直接使用RLHF提升或降低目标输出概率|Modify ChatGLM output with only RLHF

程序员延寿指南 | A programmer's guide to live longer

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

Conversational Recommender System (CRS) paper list. 对话推荐系统论文列表

CRSLab is an open-source toolkit for building Conversational Recommender System (CRS).

User-Centric Conversational Recommendation with Multi-Aspect User Modeling (UCCR)