Pinned Repositories
absa-llm-augmentation
absa_llm
active-prompt
Source code for the paper "Active Prompting with Chain-of-Thought for Large Language Models"
agents
An Open-source Framework for Autonomous Language Agents
AgentVerse
🤖 AgentVerse 🪐 provides a flexible framework that simplifies the process of building custom multi-agent environments for large language models (LLMs).
ai-app
本项目旨在分享人工智能相关应用技术以及实战经验，包括大模型、语音合成、数字人、图像生成等。
ChatGPT-Next-Web
One-Click to deploy well-designed ChatGPT web UI on Vercel. 一键拥有你自己的 ChatGPT 网页服务。
extract_news_elements
JittorLLMs
计图大模型推理库，具有高性能、配置要求低、中文支持好、可移植等特点
wiseflow
wiseflow（首席情报官）是一个完备的领域（行业）开源信息情报获取与管理系统，用户既可以针对已有信源自行编写专有爬虫，使用本系统进行完备的流程管理，甚至一键生成报告，同时也可以订阅我们专业的信息情报服务。
RayJue's Repositories
RayJue/Anima
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
RayJue/Awesome-Chinese-LLM
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。
RayJue/Awesome-LLM4IE-Papers
Awesome papers about generative Information Extraction (IE) using Large Language Models (LLMs)
RayJue/Awesome-LLMs-Datasets
Summarize existing representative LLMs text datasets.
RayJue/build_MiniLLM_from_scratch
从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)
RayJue/CoLLiE
Collaborative Training of Large Language Models in an Efficient Way
RayJue/dolphin-2.5-mixtral-8x7b-GPTQ
This Dolphin is really good at coding, it has been trained with a lot of coding data. It is very obedient but it is not DPO tuned - so you still might need to encourage it in the system prompt.
RayJue/fastRAG
Efficient Retrieval Augmentation and Generation Framework
RayJue/GoMate
GoMate：RAG Framework within Reliable input,Trusted output
RayJue/GPTQModel
An easy-to-use LLM quantization and inference toolkit based on GPTQ algorithm (weight-only quantization).
RayJue/GraphragTest
提供了一种gpt大模型平替解决方案实现利用非gpt大模型去使用Graphrag，支持多类型大模型如本地大模型(Ollama)、阿里云通义千问、百度文心千帆、智谱ChatGML、讯飞星火认知、Ollama、Moonshot AI、Google Gemini等。示例代码使用阿里的通义千问大模型，其他大模型使用方式相同。
RayJue/kotaemon
An open-source RAG-based tool for chatting with your documents.
RayJue/layoutocr_magic_llava
RayJue/llama-recipes
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.
RayJue/llm-action
本项目旨在分享大模型相关技术原理以及实战经验。
RayJue/LLM-Dojo
欢迎来到 LLM-Dojo，这里是一个开源大模型学习场所，使用简洁且易阅读的代码构建模型训练框架(支持各种主流模型如Qwen、Llama、GLM等等)、RLHF框架(DPO/CPO/KTO/PPO)等各种功能。👩🎓👨🎓
RayJue/LLM-Pruner
[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.
RayJue/LLocalSearch
LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progress of the agents and the final answer. No OpenAI or Google API keys are needed.
RayJue/long-context-attention
USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference
RayJue/Megatron-LM
Ongoing research training transformer models at scale
RayJue/MemLong
RayJue/OneLLM
[CVPR 2024] OneLLM: One Framework to Align All Modalities with Language
RayJue/pandas-ai
Chat with your database (SQL, CSV, pandas, polars, mongodb, noSQL, etc). PandasAI makes data analysis conversational using LLMs (GPT 3.5 / 4, Anthropic, VertexAI) and RAG.
RayJue/Question-Rewriter
This includes the code for generating data and training the rewriter using DPO. The DPO training code is derived from https://github.com/eric-mitchell/direct-preference-optimization with minor modifications.
RayJue/ring-flash-attention
Ring attention implementation with flash attention
RayJue/RPG-DiffusionMaster
[ICML 2024] Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs (PRG)
RayJue/rtp-llm
RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
RayJue/search_with_ai
🤖 Free Search with AI, 💡 Open-Source Perplexity, 📍 Support Ollama/SearXNG, Support Docker deployment. 让AI大模型和搜索引擎回答你的问题，支持本地大模型(Ollama)、聚合搜索引擎SearXNG，支持Docker一键部署。
RayJue/TAG-Bench
TAG-Bench: A benchmark for table-augmented generation (TAG)
RayJue/TC-RAG
the official GitHub repository for TC-RAG (Turing-Complete RAG)