KomeijiForce

Active_Passive_Constraint_Koishiday_2024

[NeurIPS 2024] An advanced persona-driven role-playing system with global faithfulness quantification and optimization. In memory of the Koishi's Day of 2024.

AutoPersona

自动从脏网页文本中提取角色人设信息的中文llama-3模型

CoTAM

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

ELECTRA-NRC

The official implementation for paper "Evaluate Confidence Instead of Perplexity for Commonsense Reasoning"

EmojiLM

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

Incubator

[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 instruction as input. The incubation is based on a llama-2-7b fine-tuned on Huggingface Meta Data and Self-Diversification.

MetaIE

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.

SemEval2023_Task10

TextGrafting

[EMNLP2024] Official Implementation of the paper "Text Grafting: Near-Distribution Weak Supervision for Minority Classes in Text Classification"

X-NER

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

KomeijiForce/MetaIE

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.

KomeijiForce/CoTAM

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

KomeijiForce/EmojiLM

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

KomeijiForce/Incubator

[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 instruction as input. The incubation is based on a llama-2-7b fine-tuned on Huggingface Meta Data and Self-Diversification.

KomeijiForce/Active_Passive_Constraint_Koishiday_2024

[NeurIPS 2024] An advanced persona-driven role-playing system with global faithfulness quantification and optimization. In memory of the Koishi's Day of 2024.

KomeijiForce/SemEval2023_Task10

KomeijiForce/TextGrafting

[EMNLP2024] Official Implementation of the paper "Text Grafting: Near-Distribution Weak Supervision for Minority Classes in Text Classification"

KomeijiForce/X-NER

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

KomeijiForce/AutoPersona

自动从脏网页文本中提取角色人设信息的中文llama-3模型

KomeijiForce/ELECTRA-NRC

The official implementation for paper "Evaluate Confidence Instead of Perplexity for Commonsense Reasoning"

KomeijiForce/KomeijiForce.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

KomeijiForce/TouhouQANet

Resources of TouhouQANet, Touhou Knowledge-125, and Touhou Knowledge Patching Codes.