Website

THUNLP

Natural Language Processing Lab at Tsinghua University

  • 16 productos activos

Portafolio de productos consolidado

  • ChatEval

    Codes for our paper "ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate"

    Llm OrchestrationOpen Source
  • Few-NERD

    Code and data of ACL 2021 paper "Few-NERD: A Few-shot Named Entity Recognition Dataset"

    Machine Learning Model TrainingOpen Source
  • FewRel

    A Large-Scale Few-Shot Relation Extraction Dataset

    Nlp Text AnalysisOpen Source
  • InfLLM

    The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory"

    Llm OrchestrationOpen Source
  • JustRL

    [ICLR 2026 Blogpost Track Poster] JustRL: Scaling a 1.5B LLM with a Simple RL Recipe

    Llm OrchestrationOpen Source
  • KB2E

    Knowledge Graph Embeddings including TransE, TransH, TransR and PTransE

    Knowledge Graph ManagementOpen Source
  • OpenAttack

    An Open-Source Package for Textual Adversarial Attack.

    Nlp Text AnalysisOpen Source
  • OpenBackdoor

    An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)

    Nlp Text AnalysisOpen Source
  • OpenDelta

    A plug-and-play library for parameter-efficient-tuning (Delta Tuning)

    Machine Learning Model TrainingOpen Source
  • OpenHowNet

    Core Data of HowNet and OpenHowNet Python API

    Knowledge Base ManagementOpen Source
  • ProactiveAgent

    A LLM-based Agent that predict its tasks proactively.

    Llm OrchestrationOpen Source
  • TAADpapers

    Must-read Papers on Textual Adversarial Attack and Defense

    Nlp Text AnalysisOpen Source
  • THUCTC

    An Efficient Chinese Text Classifier

    Nlp Text AnalysisOpen Source
  • TritonBench

    TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators

    Llm OrchestrationOpen Source
  • UltraChat

    Large-scale, Informative, and Diverse Multi-round Chat Data (and Models)

    Chatbot PlatformOpen Source
  • WantWords

    An open-source online reverse dictionary.

    Nlp Text AnalysisOpen Source

Perfil de la empresa y estrategia

Laboratorio de Procesamiento de Lenguaje Natural en la Universidad de Tsinghua. THUNLP mantiene 14 proyectos de código abierto en GitHub, incluyendo WantWords, UltraChat y KB2E. Lenguajes principales: JavaScript, Python, C++.

Presencia de código abierto

16 repositorios18.9K estrellas
Visitar la organización en GitHub

Save & manage the vendor's products in Productapp.

Save and manage this vendor's products in Productapp.

Start free trial