RayJue's repositories
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
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。
Awesome-LLM4IE-Papers
Awesome papers about generative Information Extraction (IE) using Large Language Models (LLMs)
Awesome-LLMs-Datasets
Summarize existing representative LLMs text datasets.
build_MiniLLM_from_scratch
从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)
CoLLiE
Collaborative Training of Large Language Models in an Efficient Way
FlagEmbedding
Retrieval and Retrieval-augmented LLMs
fsdp_qlora
Training LLMs with QLoRA + FSDP
g1
g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains
GoMate
GoMate：RAG Framework within Reliable input,Trusted output
GPTQModel
An easy-to-use LLM quantization and inference toolkit based on GPTQ algorithm (weight-only quantization).
instructor
structured outputs for llms
kotaemon
An open-source RAG-based tool for chatting with your documents.
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.
llm-action
本项目旨在分享大模型相关技术原理以及实战经验。
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。👩🎓👨🎓
llm-graph-builder
Neo4j graph construction from unstructured data using LLMs
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.
long-context-attention
USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference
Megatron-LM
Ongoing research training transformer models at scale
ms-swift
Use PEFT or Full-parameter to finetune 300+ LLMs or 80+ MLLMs. (Qwen2, GLM4v, Internlm2.5, Yi, Llama3.1, Llava-Video, Internvl2, MiniCPM-V-2.6, Deepseek, Baichuan2, Gemma2, Phi3-Vision, ...)
ring-flash-attention
Ring attention implementation with flash attention
rtp-llm
RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
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。
sparrow
Data processing with ML and LLM
TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
ThinkDB
With ThinkDB, you can easily dive into your databases without needing to be an SQL wizard! 🧙♂️✨ The AI in ThinkDB gets what you’re trying to do and helps turn your ideas into the perfect query. Whether you’re a seasoned pro or just getting started, ThinkDB makes it super easy to find, explore, and manage your data—all in a way that feels natural.
unstract
No-code LLM Platform to launch APIs and ETL Pipelines to structure unstructured documents