liulj's repositories
NLP-Interview-Notes
本项目是作者们根据个人面试和经验总结出的自然语言处理(NLP)面试准备的学习笔记与资料,该资料目前包含 自然语言处理各领域的 面试题积累。
Algorithm-Practice-in-Industry
搜索、推荐、广告、用增等工业界实践文章收集(来源:知乎、Datafuntalk、技术公众号)
automated-essay-scoring
作文自动打分系统
awesome-pretrained-chinese-nlp-models
Awesome Pretrained Chinese NLP Models,高质量中文预训练模型&大模型&多模态模型&大语言模型集合
BERT-BiLSTM-CRF-NER
Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services
deeplearning
深度学习相关的模型训练、评估和预测相关代码
dssm
DSSM and Multi-View DSSM
finetune_dataset_maker
为ChatGLM设计的微调数据集生成工具,速来制作自己的猫娘。
fun-rec
推荐系统入门教程,在线阅读地址:https://datawhalechina.github.io/fun-rec/
GPT2-Chinese
Chinese version of GPT2 training code, using BERT tokenizer.
gpt_academic
为ChatGPT/GLM提供实用化交互界面,特别优化论文阅读/润色/写作体验,模块化设计,支持自定义快捷按钮&函数插件,支持Python和C++等项目剖析&自译解功能,PDF/LaTex论文翻译&总结功能,支持并行问询多种LLM模型,支持chatglm2等本地模型。兼容文心一言, moss, llama2, rwkv, claude2, 通义千问, 书生, 讯飞星火等。
GRUEN
GRUEN for Evaluating Linguistic Quality of Generated Text (EMNLP 2020 Findings)
How-to-use-Transformers
Transformers 库快速入门教程
keras_bert_classification
keras bert classification and dssm
LMOps
General technology for enabling AI capabilities w/ LLMs and MLLMs
multi-task-learning
TensorFlow implementation of multi-task learning architectures, incl. MMoE & PLE, on wechat dataset
nstools
Some meaningless nscripter tools.
Open-Assistant
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
paper-reading
深度学习经典、新论文逐段精读
pke_zh
pke_zh, python keyphrase extraction for chinese(zh). 中文关键词或关键句提取工具。
ranking
Learning to Rank in TensorFlow
SimCSE
EMNLP'2021: SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
SimpleVQA
A Deep Learning based No-reference Quality Assessment Model for UGC Videos
TensorFlow_Practice
推荐系统/计算广告相关仓库,个人博客https://jesse-csj.github.io/
text_matching
常用文本匹配模型tf版本,数据集为QA_corpus,持续更新中
transformers_tasks
⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.
Unbiased_LambdaMart
Code for WWW'19 "Unbiased LambdaMART: An Unbiased Pairwise Learning-to-Rank Algorithm", which is based on LightGBM