Grok open release

Open-Sora: Democratizing Efficient Video Production for All

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

Retrieval and Retrieval-augmented LLMs

⚡机器学习实战（Python3）：kNN、决策树、贝叶斯、逻辑回归、SVM、线性回归、树回归

机器学习算法python实现

Example models using DeepSpeed

Basic Machine Learning and Deep Learning

A Next-Generation Training Engine Built for Ultra-Large MoE Models

Minimal keyword extraction with BERT

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

A simple, easy-to-hack GraphRAG implementation

VirtualWife是一个虚拟数字人项目，支持B站直播，支持openai、ollama

knowledge graph知识图谱,从零开始构建知识图谱

自然语言处理工具Macropodus，基于Albert+BiLSTM+CRF深度学习网络架构，中文分词，词性标注，命名实体识别，新词发现，关键词，文本摘要，文本相似度，科学计算器，中文数字阿拉伯数字(罗马数字)转换，中文繁简转换，拼音转换。tookit(tool) of NLP，CWS(chinese word segnment)，POS(Part-Of-Speech Tagging)，NE…

[ICLR 2024] Lemur: Open Foundation Models for Language Agents

Code repository for supporting the paper "Atlas Few-shot Learning with Retrieval Augmented Language Models",(https//arxiv.org/abs/2208.03299)

This is an implementation of the paper: Searching for Best Practices in Retrieval-Augmented Generation (EMNLP2024)

EasyTPP: Towards Open Benchmarking Temporal Point Processes

LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.

An exploration for Eventline (important news Rank organized by pulic time)，针对某一事件话题下的新闻报道集合，通过使用docrank算法，对新闻报道进行重要性识别，并通过新闻报道时间挑选出时间线上重要新闻。

pytorch复现stable diffusion

Python implementation of an N-gram language model with Laplace smoothing and sentence generation.

a tool for calcualting character n-gram F score

（已失效）我去图书馆 免抓包 获取Cookie

[ACL 2024 Oral] This is the code repo for our ACL‘24 paper "MARVEL: Unlocking the Multi-Modal Capability of Dense Retrieval via Visual Module Plugin".

[ACL 2024 main] Aligning Large Language Models with Human Preferences through Representation Engineering (https://aclanthology.org/2024.acl-long.572/)