vansin

vansin

Geek Repo

Location:New York

Home Page:https://vansin.top

Github PK Tool:Github PK Tool

vansin's starred repositories

InternLM

Official release of InternLM2 7B and 20B base and chat models. 200K context support

Language:PythonLicense:Apache-2.0Stargazers:5437Issues:49Issues:291

xtuner

An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

Language:PythonLicense:Apache-2.0Stargazers:2999Issues:30Issues:383

OpenAI_Agent_Swarm

HAAS = Hierarchical Autonomous Agent Swarm - "Resistance is futile!"

Language:PythonLicense:MITStargazers:2936Issues:111Issues:28

lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Language:PythonLicense:Apache-2.0Stargazers:2899Issues:27Issues:896

InternLM-XComposer

InternLM-XComposer2 is a groundbreaking vision-language large model (VLLM) excelling in free-form text-image composition and comprehension.

HuixiangDou

HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance

Language:PythonLicense:BSD-3-ClauseStargazers:1067Issues:15Issues:25

minisora

MiniSora: A community aims to explore the implementation path and future development direction of Sora.

Language:PythonLicense:Apache-2.0Stargazers:1065Issues:16Issues:62

lagent

A lightweight framework for building LLM-based agents

Language:PythonLicense:Apache-2.0Stargazers:965Issues:11Issues:44

Tutorial

LLM Tutorial

VLMEvalKit

Open-source evaluation toolkit of large vision-language models (LVLMs), support GPT-4v, Gemini, QwenVLPlus, 50+ HF models, 20+ benchmarks

Language:PythonLicense:Apache-2.0Stargazers:534Issues:8Issues:69

EmoLLM

心理健康大模型、LLM、The Big Model of Mental Health、Finetune、InternLM2、Qwen、ChatGLM、Baichuan、DeepSeek、Mixtral、LLama3

Language:PythonLicense:MITStargazers:451Issues:1Issues:24

Llama3-Tutorial

Llama3-Tutorial(XTuner、LMDeploy、OpenCompass)

Language:PythonLicense:Apache-2.0Stargazers:327Issues:7Issues:13

ScaleLLM

A high-performance inference system for large language models, designed for production environments.

Language:C++License:Apache-2.0Stargazers:305Issues:14Issues:65

agentlego

Enhance LLM agents with versatile tool APIs

Language:PythonLicense:Apache-2.0Stargazers:299Issues:8Issues:5

Agent-FLAN

[ACL2024 Findings] Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models

Multi-Type-TD-TSR

Extracting Tables from Document Images using a Multi-stage Pipeline for Table Detection and Table Structure Recognition:

Language:Jupyter NotebookLicense:MITStargazers:248Issues:9Issues:14
Language:PythonLicense:Apache-2.0Stargazers:219Issues:7Issues:55

OpenAOE

LLM Group Chat Framework: chat with multiple LLMs at the same time. 大模型群聊框架:同时与多个大语言模型聊天。

Language:TypeScriptLicense:Apache-2.0Stargazers:201Issues:6Issues:7
Language:Jupyter NotebookLicense:CC-BY-4.0Stargazers:93Issues:4Issues:1

Roleplay-with-XiYou

基于《西游记》原文、白话文、ChatGPT生成数据制作的,以InternLM2微调的角色扮演多LLM聊天室。 本项目将介绍关于角色扮演类 LLM 的一切,从数据获取、数据处理,到使用 XTuner 微调并部署至 OpenXLab,再到使用 LMDeploy 部署,以 openai api 的方式接入简单的聊天室,并可以观看不同角色的 LLM 互相交流、互怼。

Language:PythonLicense:Apache-2.0Stargazers:61Issues:2Issues:1

Hand-on-RAG

顾名思义:手搓的RAG

Language:PythonStargazers:52Issues:0Issues:1

InternEvo_bak

InternEvo is a high-performance training system for giant models.

Language:PythonLicense:Apache-2.0Stargazers:37Issues:1Issues:0

pytorch_sphinx_theme

PyTorch Sphinx Theme

Language:CSSLicense:MITStargazers:36Issues:1Issues:0

MiniSora-DiT

minisora-DiT, a DiT reproduction based on XTuner from the open source community MiniSora

Language:PythonLicense:Apache-2.0Stargazers:31Issues:5Issues:0

BaJie-Chat

八戒-Chat是利用《西游记》剧本中所有关于猪八戒的台词和语句,以及Chat-GPT-3.5生成的相关问题结果,基于Internlm进行QLoRA微调得到的模仿猪八戒语气的聊天语言模型。

Language:PythonLicense:Apache-2.0Stargazers:20Issues:1Issues:1
Language:PythonLicense:Apache-2.0Stargazers:18Issues:0Issues:0

RobotsWorld4Reality

🤖The Real World of Functional AI Robots🤖

Language:PythonLicense:Apache-2.0Stargazers:10Issues:0Issues:0

InternLM-LeaningNote

Study Notes for InternLM

Stargazers:2Issues:0Issues:0