BOBrown

LLFC

[NeurIPS 2023] Code release for "Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity"

ThinkMatch

A research protocol for deep graph matching.

awesome-ml4co

Awesome machine learning for combinatorial optimization papers.

Bench2Drive

Closed-loop multi-ability evaluation of end-to-end autonomous driving algorithms

gptpdf

Using GPT to parse PDF

StructEqTable-Deploy

A High-efficiency Open-source Toolkit for Table-to-Latex Task

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

PDF-Extract-Kit

A Comprehensive Toolkit for High-Quality PDF Content Extraction

graphrag

A modular graph-based Retrieval-Augmented Generation (RAG) system

MinerU

A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具，支持PDF/网页/多格式电子书提取。

SciGLM

SciGLM: Training Scientific Language Models with Self-Reflective Instruction Annotation and Tuning

VLMEvalKit

Open-source evaluation toolkit of large vision-language models (LVLMs), support ~100 VLMs, 30+ benchmarks

xtuner

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

GroundingGPT

[ACL 2024] GroundingGPT: Language-Enhanced Multi-modal Grounding Model

gpt-researcher

GPT based autonomous agent that does online comprehensive research on any given topic

GAOKAO-Eval

OmniCorpus

OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text

DocGenome

DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Models

lancedb

Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!

ambientGPT

llm.c

LLM training in simple, raw C/CUDA

LeapAD

Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Driving

InternVL

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的可商用开源多模态对话模型

UniMERNet

UniMERNet: A Universal Network for Real-World Mathematical Expression Recognition

LeanCopilot

LLMs as Copilots for Theorem Proving in Lean

table-transformer

Table Transformer (TATR) is a deep learning model for extracting tables from unstructured documents (PDFs and images). This is also the official repository for the PubTables-1M dataset and GriTS evaluation metric.

Megatron-LM

Ongoing research training transformer models at scale

Once-for-Both

[CVPR'24] Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression

InterGPS

Data and Code for ACL 2021 Paper "Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning"

sycamore

🍁 Sycamore is an LLM-powered search and analytics platform for unstructured data.