izhx

rustdesk

An open-source remote desktop application designed for self-hosting, as an alternative to TeamViewer.

open-webui

User-friendly WebUI for LLMs (Formerly Ollama WebUI)

LLM101n

LLM101n: Let's build a Storyteller

PlayCover

Community fork of PlayCover

sglang

SGLang is yet another fast serving framework for large language models and vision language models.

text-embeddings-inference

A blazing fast inference solution for text embeddings models

chameleon

Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

SWE-bench

[ICLR 2024] SWE-Bench: Can Language Models Resolve Real-world Github Issues?

LLMCompiler

[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling

FlashRAG

⚡FlashRAG: A Python Toolkit for Efficient RAG Research

aligo

🔥简单、易用、可扩展的阿里云盘 API 接口库🚀

nlp-phd-global-equality

A repo for open resources & information for people to succeed in PhD in CS & career in AI / NLP

flash-linear-attention

Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

Generative-AI

[TPAMI 2023] Multimodal Image Synthesis and Editing: The Generative AI Era

bm25s

Fast lexical search library implementing BM25 in Python using Numpy and Scipy

MRL

Code repository for the paper - "Matryoshka Representation Learning"

DreamLLM

[ICLR 2024 Spotlight] DreamLLM: Synergistic Multimodal Comprehension and Creation

SpeculativeDecodingPapers

📰 Must-read papers and blogs on Speculative Decoding ⚡️

CapsFusion

[CVPR 2024] CapsFusion: Rethinking Image-Text Data at Scale

LooGLE

ACL 2024 | LooGLE: Long Context Evaluation for Long-Context Language Models

multires-conv

Sequence Modeling with Multiresolution Convolutional Memory (ICML 2023)

Imbalance-VLM

AIR-Bench

AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark

LLM_Agent_Memory_Survey

bm25_pt

minimal pytorch implementation of bm25 (with sparse tensors)

xCodeEval

xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval

swim-ir

SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 languages, generated using PaLM 2 and summarize-then-ask prompting.

understanding_llm_benchmarks

Understanding the correlation between different LLM benchmarks

ChatIR

Official repository of "Chatting Makes Perfect: Chat-based Image Retrieval"

Visual-C3

Towards Real-World Writing Assistance: A Chinese Character Checking Benchmark with Faked and Misspelled Characters