Starred repositories
Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Empowering RAG with a memory-based data interface for all-purpose applications!
A useful list of NLP(Natural Language Processing) resources
Project for the paper entitled `Instruction Tuning for Large Language Models: A Survey`
LLM prompts, llama3 prompts, llama2 prompts
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without …
多模态中文LLaMA&Alpaca大语言模型（VisualCLA）
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。
Make your GenAI Apps Safe & Secure 🚀 Test & harden your system prompt
Prompt engineering is using natural language to produce a desired response from a large language model (LLM).
《动手学大模型Dive into LLMs》系列编程实践教程
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
Official PyTorch Implementation of EMoE: Unlocking Emergent Modularity in Large Language Models [main conference @ NAACL2024]
Facebook Low Resource (FLoRes) MT Benchmark
A large-scale 7B pretraining language model developed by BaiChuan-Inc.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
A UI made in Pyside6 to make training LoRA/LoCon and other LoRA type models in sd-scripts easy
Scripts for fine-tuning Llama2 via SFT and DPO.
Finetuning InstructLLaMA on consumer hardware (copy from https://github.com/tloen/alpaca-lora)
BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）