Pinned Repositories
CKBQA
This repository contains a Chinese KBQA dataset expanded from CCKS CKBQA Competition Dataset.
Crake
Source code for Crake, NAACL 2022 Findings
DWIE
DWIE (Deutsche Welle corpus for Information Extraction) dataset. Introduced in our "DWIE: an entity-centric dataset for multi-task document-level information extraction" paper (accepted in Information Processing and Management)
Firefly
Firefly(流萤): 中文对话式大语言模型(全量微调+QLoRA)，支持微调Llma2、Llama、Baichuan、InternLM、Ziya、Bloom等大模型
gnn-tutorial
This repository contains 2 gnn homework.
jerex
PyTorch code for JEREX: Joint Entity-Level Relation Extractor
LLMaAA
The official repository for paper "LLMaAA: Making Large Language Models as Active Annotators"
OpenRLHF
An Easy-to-use, Scalable and High-performance RLHF Framework (Support 70B+ full tuning & LoRA & Mixtral & KTO)
R-DocRED
TaG
The official repository for ACL 2023 paper "A Novel Table-to-Graph Generation Approach for Document-Level Joint Entity and Relation Extraction"
ridiculouz's Repositories
ridiculouz/LLMaAA
The official repository for paper "LLMaAA: Making Large Language Models as Active Annotators"
ridiculouz/TaG
The official repository for ACL 2023 paper "A Novel Table-to-Graph Generation Approach for Document-Level Joint Entity and Relation Extraction"
ridiculouz/CKBQA
This repository contains a Chinese KBQA dataset expanded from CCKS CKBQA Competition Dataset.
ridiculouz/R-DocRED
ridiculouz/Crake
Source code for Crake, NAACL 2022 Findings
ridiculouz/DWIE
DWIE (Deutsche Welle corpus for Information Extraction) dataset. Introduced in our "DWIE: an entity-centric dataset for multi-task document-level information extraction" paper (accepted in Information Processing and Management)
ridiculouz/Firefly
Firefly(流萤): 中文对话式大语言模型(全量微调+QLoRA)，支持微调Llma2、Llama、Baichuan、InternLM、Ziya、Bloom等大模型
ridiculouz/gnn-tutorial
This repository contains 2 gnn homework.
ridiculouz/jerex
PyTorch code for JEREX: Joint Entity-Level Relation Extractor
ridiculouz/OpenRLHF
An Easy-to-use, Scalable and High-performance RLHF Framework (Support 70B+ full tuning & LoRA & Mixtral & KTO)
ridiculouz/trlx
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)