Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)

[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models

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。

🩹Editing large language models within 10 seconds⚡

A cloud-native vector database, storage for next generation AI applications

第一个开源的基于QLoRA的33B中文大语言模型First QLoRA based open source 33B Chinese LLM

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现包括二次预训练、有监督微调、奖励建模、强化学习训练。

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

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

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

⚡ Building applications with LLMs through composability ⚡

A collection of phenomenons observed during the scaling of big foundation models, which may be developed into consensus, principles, or laws in the future

Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型

An Open Toolkit for Knowledge Graph Extraction and Construction published at EMNLP2022 System Demonstrations.

🎉 Repo for LaWGPT, Chinese-Llama tuned with Chinese Legal knowledge. 基于中文法律知识的大语言模型

🔊 Text-Prompted Generative Audio Model

中文LLaMA&Alpaca大语言模型+本地CPU/GPU部署 (Chinese LLaMA & Alpaca LLMs)

⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡

Unsupervised text tokenizer for Neural Network-based text generation.

Example models using DeepSpeed

🤖 A list of open LLMs available for commercial use.

langchain-ChatGLM, local knowledge based ChatGLM with langchain ｜ 基于本地知识的 ChatGLM 问答

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

A distributed, fast open-source graph database featuring horizontal scalability and high availability

Panda: 海外中文开源大语言模型，基于 Llama-7B, -13B, -33B, -65B 进行中文领域上的持续预训练。

A graph database that supports more than 100+ billion data, high performance and scalability (Include OLTP Engine & REST-API & Backends)

A system for CCKS2019-CKBQA, whose single system reach 0.69 and ensemble system reach 0.73