Optimized FP16/BF16 x FP4 GPU kernels for AMD GPUs

Koishi's Day 2025 Paper (NeurIPS 2025): "Codifying Character Logic in Role-Playing"

Train your AI self, amplify you, bridge the world

[ACL2025 Oral] Cuckoo: A Series of IE Free Riders Using LLM's Resources to Scale up Themselves.

Official Implementation for "Linear Correlation in LM’s Compositional Generalization and Hallucination"

Official Implementation for "Less than One-shot: Named Entity Recognition via Extremely Weak Supervision"

Official Implementation for "EmojiLM: Modeling the New Emoji Language"

[EMNLP2024] This repo is the official implementation for Incubating Text Classifiers Following User Instruction with Nothing but LLM. We allow users to get a personalized classifier with only the i…

This is a meta-model distilled from LLMs for information extraction. This is an intermediate checkpoint that can be well-transferred to all kinds of downstream information extraction tasks.

Official Implementation of the ACL2024 Findings paper "Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation"

tracking papers, datasets, and models of "large language model (LLM) for time series"

Source code for InBedder, an instruction-following text embedder

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Models and examples built with TensorFlow

This project provides an unsupervised framework for mining and tagging quality phrases on text corpora with pretrained language models (KDD'21).

Usage, novelty, and metadata of code repositories.

ACL2020 Tutorial: Open-Domain Question Answering

Code for the paper "Contextualized Weak Supervision for Text Classification"

Code of EMNLP 2020 (Findings) paper: SeNsER: Learning Cross-Building Sensor Metadata Tagger.

Code for the paper "NetTaxo: Automated Topic Taxonomy Constructionfrom Text-Rich Network"

Graph Markov Neural Networks

Coronavirus analysis

Raw-to-End Name Entity Recognition in Social Media

CrossWeigh: Training Named Entity Tagger from Imperfect Annotations

On the Variance of the Adaptive Learning Rate and Beyond

Arabic NER system with a strong performance

A curated resource for taxonomy research

Repo for counting stars and contributing. Press F to pay respect to glorious developers.