TGLTommyAI

grok-1

Grok open release

OpenDevin

🐚 OpenDevin: Code Less, Make More

gorilla

Gorilla: An API store for LLMs

guided-diffusion

awesome-LLMs-In-China

**大模型

docarray

Represent, send, store and search multimodal data

unlimiformer

Public repo for the NeurIPS 2023 paper "Unlimiformer: Long-Range Transformers with Unlimited Length Input"

AQLM

Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.pdf

chatdocs

Chat with your documents offline using AI.

StreamMultiDiffusion

Official code for the paper "StreamMultiDiffusion: Real-Time Interactive Generation with Region-Based Semantic Control."

Leaderboard

SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech Recognition.

EasyJailbreak

An easy-to-use Python framework to generate adversarial jailbreak prompts.

Agent-FLAN

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

GiT

🔥 [ECCV2024] Official Implementation of "GiT: Towards Generalist Vision Transformer through Universal Language Interface"

video-mamba-suite

The suite of modeling video with Mamba

lm-inference-engines

Comparison of Language Model Inference Engines

EfficientVMamba

Code Implementation of EfficientVMamba

FouriScale

Official implementation of FouriScale (ECCV2024)

Griffon

【ECCV2024】The official repo of Griffon series

DevBench

A Comprehensive Benchmark for Software Development.

MAVEN-ERE

Source code and dataset for EMNLP 2022 paper "MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction".

ragged

Retrieval Augmented Generation Generalized Evaluation Dataset

DRAGIN

Source code of DRAGIN, ACL 2024 main conference Long Paper

Veagle

Enhancement in Multimodal Representation Learning.

Character100

Code and data for COLING2024 paper "Characteristic AI Agents via Large Language Models".

agent-os

High performance (LLM-) agents execution environment with production in mind.

ChartInstruct

novelqa.github.io

RefLDMSeg

SMART

SMART: Submodular Data Mixture Strategy for Efficient and Effective Instruction Tuning