UnaXff's Stars
chroma-core/chroma
the AI-native open-source embedding database
BinNong/meet-libai
李白 :bust_in_silhouette: 作为唐代杰出诗人,其诗歌作品在**文学史上具有重要地位。近年来,随着数字技术和人工智能的快速发展,传统文化普及推广的形式也面临着创新与变革。国内外对于李白诗歌的研究虽已相当深入,但在数字化、智能化普及方面仍存在不足。因此,本项目旨在通过构建李白知识图谱,结合大模型训练出专业的AI智能体,以生成式对话应用的形式,推动李白文化的普及与推广。
yuntianhe2014/Easy-RAG
一个适合学习、使用、自主扩展的RAG【检索增强生成】系统!可联网做AI搜索
awslabs/decode-answer-logical-form
amazon-science/tree-of-traversals
Zeyi-Lin/LLM-Finetune
大语言模型微调,Qwen2、GLM4指令微调
datawhalechina/self-llm
《开源大模型食用指南》基于Linux环境快速部署开源大模型,更适合**宝宝的部署教程
QwenLM/Qwen2
Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.
lanyunshi/Multi-hopComplexKBQA
apple/corenet
CoreNet: A library for training deep neural networks
run-llama/modal_finetune_sql
iSenses/YANL2GQL
Yet anothter NL2GQL
liaomingyue/liaomingyue-python-master
self-ms/text-to-text-fine-tuning-mt5-based
for question answering, text to SPARQL and etc.
bojone/t5_in_bert4keras
整理一下在keras中使用T5模型的要点
nlp-tlp/Rel2Graph
zhiqix/NL2GQL
The LLM of NL2GQL with NebulaGraph or Neo4j
wmathor/nlp-tutorial
Natural Language Processing Tutorial for Deep Learning Researchers
RUCKBReasoning/RESDSQL
The Pytorch implementation of RESDSQL (AAAI 2023).
SunnyGJing/t5-pegasus-chinese
基于GOOGLE T5中文生成式模型的摘要生成/指代消解,支持batch批量生成,多进程
shuxinyin/T5-NLP
Explore different chinese nlp tasks by using t5/mt5/t5-pegasus like text-classification, text-summary and so on.
salesforce/CodeT5
Home of CodeT5: Open Code LLMs for Code Understanding and Generation
AKSW/LMs4Text2SPARQL
Finetuning LLMs for the Text2Sparql task
920232796/bert_seq2seq_DDP
bert_seq2seq的DDP版本,支持bert、roberta、nezha、t5、gpt2等模型,支持seq2seq、ner、关系抽取等任务,无需添加额外代码,轻松启动DDP多卡训练。
920232796/bert_seq2seq
pytorch实现 Bert 做seq2seq任务,使用unilm方案,现在也可以做自动摘要,文本分类,情感分析,NER,词性标注等任务,支持t5模型,支持GPT2进行文章续写。
MaseratiD/S2CTrans
pkumod/gStore
gStore - a graph based RDF triple store.
pkumod/CCKS-CKBQA-DATASET
Datasets for CCKS Chinese KBQA.
donglixp/coarse2fine
Alex-Fabbri/lang2logic-PyTorch
PyTorch port of the paper "Language to Logical Form with Neural Attention"