heroding77

996.ICU

Repo for counting stars and contributing. Press F to pay respect to glorious developers.

ollama

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

LeetCodeAnimation

Demonstrate all the questions on LeetCode in the form of animation.（用动画的形式呈现解LeetCode题目的思路）

github-readme-stats

:zap: Dynamically generated stats for your github readmes

gpt_academic

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

cs-self-learning

计算机自学指南

open-interpreter

A natural language interface for computers

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

selenium

A browser automation framework and ecosystem.

LLaMA-Factory

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

shields

Concise, consistent, and legible badges in SVG and raster format

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

Chinese-LLaMA-Alpaca

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

flash-attention

Fast and memory-efficient exact attention

SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

Open-Sora-Plan

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

nougat

Implementation of Nougat Neural Optical Understanding for Academic Documents

InternLM

Official release of InternLM2.5 7B base and chat models. 1M context support

Voyager

An Open-Ended Embodied Agent with Large Language Models

examples

Jupyter Notebooks to help you get hands-on with Pinecone vector databases

LongLoRA

Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)

open-instruct

OSWorld

OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

SeeAct

[ICML'24] SeeAct is a system for generalist web agents that autonomously carry out tasks on any given website, with a focus on large multimodal models (LMMs) such as GPT-4V(ision).

NCISurvey

Neural Code Intelligence Survey 2024; Reading lists and resources

SeeClick

The model, data and code for the visual GUI Agent SeeClick

AwesomeNLP

此项目完成了关于 NLP-Beginner：自然语言处理入门练习 的所有任务（文本分类、信息抽取、知识图谱、机器翻译、问答系统、文本生成、Text-to-SQL、文本纠错、文本挖掘、知识蒸馏、模型加速、OCR、TTS、Prompt、embedding等），所有代码都经过测试,可以正常运行。

agent-studio

Benchmarks, environments, and toolkits for general computer agents

SheetCopilot

We release a general framework for prompting LLMs to manipulate software in a closed-loop manner.

eat_chatgpt