rayjue Goto Github PK

promptflow

Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.

promptsource

Toolkit for creating, sharing and using natural language prompts.

pythia

python_common_code_collection

收集经常用到的一些python代码

qa-civilaviationkg

基于民航业知识图谱的自动问答系统

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

quivr

Dump all your files and thoughts into your private GenerativeAI Second Brain and chat with it

qwen-agent

Agent framework and applications built upon Qwen1.5, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.

qwen2_moe_mergekit

根据Qwen2（Qwen1.5）模型生成qwen2 MoE模型的工具

r-tuning

Source code for the NAACL 2024 paper entitled "R-Tuning: Instructing Large Language Models to Say 'I Don't Know'"

rag-experiment-accelerator

The RAG Experiment Accelerator is a versatile tool designed to expedite and facilitate the process of conducting experiments and evaluations using Azure Cognitive Search and RAG pattern.

rag_survey

raptor

RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

reasoning-on-cots

Implementation of the paper: "Answering Questions by Meta-Reasoning over Multiple Chains of Thought"

recurrentgpt

Official Code for Paper: RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text

rerope

Rectified Rotary Position Embeddings

rl4f

Code for RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs. ACL 2023.

rlhf-label-tool

用于大模型 RLHF 进行人工数据标注排序的工具。A tool for manual response data annotation sorting in RLHF stage.

rotary-embedding-torch

Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch

s-lora

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

safe-rlhf

Safe-RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

salesgpt

Context-aware AI Sales Agent to automate sales outreach.

scaled-rope

science_technology_policy_integration_service

基于知识图谱的科技政策管理系统

screenshot-to-code

Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)

shukongdashi

使用知识图谱，自然语言处理，卷积神经网络等技术，基于python语言，设计了一个数控领域故障诊断专家系统

sq-llava

Visual self-questioning for large vision-language assistant.

stablediffusion

High-Resolution Image Synthesis with Latent Diffusion Models

stlr-llm

short-context transformer long-context recurrent large language model

taskingai

The open source platform for AI-native application development.