Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging

An awesome repository & A comprehensive survey on interpretability of LLM attention heads.

Development repository for the Triton language and compiler

A temple run game controlled using face positions.

Extending activation addition to broad skills and multiple behaviours

Code and Data for EMNLP 2024 Paper "Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent"

This repo contains the code for generating the ToxiGen dataset, published at ACL 2022.

Code and Data for CIKM 2024 Paper "Does Knowledge Localization Hold True? Surprising Differences Between Entity and Relation Perspectives in Language Models"

Code and Data for EMNLP 2023 Findings Paper "MenatQA: A New Dataset for Testing the Temporal Comprehension and Reasoning Abilities of Large Language Models"

LMTuner: Make the LLM Better for Everyone

A central, open resource for data and tools related to chain-of-thought reasoning in large language models. Developed @ Samwald research group: https://samwald.info/

An unofficial implement of DeepNorm. https://arxiv.org/pdf/2203.00555.pdf

中文数据集下SimCSE+ESimCSE的实现

SOTA of SDU@AAAI2022 AD task

MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents

The repository contains the corpus data set required by the NLGIW2021 profiling task.

Code for the EMNLP 2020 paper "Program Enhanced Fact Verification with Verbalization and Graph Attention Network"

ICLR 2022 Paper, SOTA Table Pre-training Model, TAPEX: Table Pre-training via Learning a Neural SQL Executor

Data and Code for ICLR2020 Paper "TabFact: A Large-scale Dataset for Table-based Fact Verification"

Chinese Word2vec Medicine，中文医学词向量

CodeHub is an iOS application written using Xamarin