Zhang Handuo's starred repositories
Megatron-LM
Ongoing research training transformer models at scale
meet-libai
李白 :bust_in_silhouette: 作为唐代杰出诗人，其诗歌作品在**文学史上具有重要地位。近年来，随着数字技术和人工智能的快速发展，传统文化普及推广的形式也面临着创新与变革。国内外对于李白诗歌的研究虽已相当深入，但在数字化、智能化普及方面仍存在不足。因此，本项目旨在通过构建李白知识图谱，结合大模型训练出专业的AI智能体，以生成式对话应用的形式，推动李白文化的普及与推广。
text2sql-schema-filter
The source code for the schema filter (question + schema only)
objectdetection_script
一些关于目标检测的脚本的改进思路代码，详细请看readme.md
OpenCodeInterpreter
OpenCodeInterpreter is a suite of open-source code generation systems aimed at bridging the gap between large language models and sophisticated proprietary systems like the GPT-4 Code Interpreter. It significantly enhances code generation capabilities by integrating execution and iterative refinement functionalities.
DataDreamer
DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤
MoneyPrinterV2
Automate the process of making money online.
WhisperSpeech
An Open Source text-to-speech system built by inverting Whisper.
CopilotKit
A framework for building custom AI Copilots 🤖 in-app AI chatbots, in-app AI Agents, & AI-powered Textareas.
leaf-playground
A framework to build scenario simulation projects where human and LLM based agents can participant in, with a user-friendly web UI to visualize simulation, support automatically evaluation on agent action level.
llmops-promptflow-template
LLMOps with Prompt Flow is a "LLMOps template and guidance" to help you build LLM-infused apps using Prompt Flow. It offers a range of features including Centralized Code Hosting, Lifecycle Management, Variant and Hyperparameter Experimentation, A/B Deployment, reporting for all runs and experiments and so on.
home-robot
Mobile manipulation research tools for roboticists
TaskWeaver
A code-first agent framework for seamlessly planning and executing data analytics tasks.
benchmark4GPT
"Our project provides 500 carefully designed questions that can be used to test and evaluate the performance of Generative Pretrained Transformer (GPT) models. The questions cover a variety of topics and domains and are designed to comprehensively examine the performance of GPT models Comprehension, creativity and logical reasoning skills.
swiss_army_llama
A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract.