qixucen

chain-of-table

HippoRAG

HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents.

Conference-Acceptance-Rate

Acceptance rates for the major AI conferences

mup

maximal update parametrization (µP)

simulated-trial-and-error

NBFNet

Official implementation of Neural Bellman-Ford Networks (NeurIPS 2021)

NeMo-Skills

A pipeline to improve skills of large language models

math

The MATH Dataset (NeurIPS 2021)

Multimodal-AND-Large-Language-Models

Paper list about multimodal and large language models, only used to record papers I read in the daily arxiv for personal needs.

LLaMA-Factory

Unify Efficient Fine-Tuning of 100+ LLMs

Multi-hopRC

:notebook_with_decorative_cover: notes for Multi-hop Reading Comprehension and open-domain question answering

clash-for-linux-backup

基于Clash Core 制作的Clash For Linux备份仓库 A Clash For Linux Backup Warehouse Based on Clash Core

MetaGPT

🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo

xLAM

DeepSpeed

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

LLM-Viewer

Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline model in a user-friendly interface.

TRAD-Official

[SIGIR 2024] TRAD: Enhancing LLM Agents with Step-Wise Thought Retrieval and Aligned Decision

R2PE

Awesome-LLM-Compression

Awesome LLM compression research papers and tools.

reinforcement-learning

Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.

sheetagent.github.io

mint-bench

Official Repo for ICLR 2024 paper MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback by Xingyao Wang*, Zihan Wang*, Jiateng Liu, Yangyi Chen, Lifan Yuan, Hao Peng and Heng Ji.

OLMo

Modeling, training, eval, and inference code for OLMo

dspy

DSPy: The framework for programming—not prompting—foundation models

EMO

Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

SwiftSage

SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks

reflexion

[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning

XoT

EMNLP 2023 Plan, Verify and Switch: Integrated Reasoning with Diverse X-of-Thoughts

LLM-Knowledge-Conflict

[ICLR'24 Spotlight] Code and Data for paper LLM Knowledge Conflict.

ControlLLM

ControlLLM: Augment Language Models with Tools by Searching on Graphs