songt's repositories
nlp-beginner-solutions
Solutions of FudanNLP/nlp-beginner: NLP上手教程 https://github.com/FudanNLP/nlp-beginner
practical-ml
Learn by experimenting on state-of-the-art machine learning models and algorithms with Jupyter Notebooks.
Alpaca-CoT
We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. Meanwhile, we created a new branch to build a Tabular LLM.（我们分别统一了丰富的IFT数据（如CoT数据，目前仍不断扩充）、多种训练效率方法（如lora，p-tun
cs231n-2017-assignment2
cs231n-2017-assignment2 浏览ipynb戳右边->
cs231n-2017-assignment3
cs231n-2017-assignment3
kaggle-SA-on-movie-reviews
sentiment-analysis-on-movie-reviews
kaggle-toxic-comment-classification
toxic comment classification
kaggle-word2vec-on-movies
Sentiment Analysis：Bag of Words Meets Bags of Popcorn
CAIL
Chinese AI & Law Challenge
ChineseAntiword
chinese anti semantic word search interface based on dict crawled from online resources, ChineseAntiword,针对中文词语的反义词查询接口
CrimeKgAssitant
Crime assistant including crime type prediction and crime consult service based on nlp methods and crime kg,罪名法务智能项目,内容包括856项罪名知识图谱, 基于280万罪名训练库的罪名预测,基于20W法务问答对的13类问题分类与法律资讯问答功能.
cs231n-2016
cs231n assignment 2016
imdb
nbviewer
LawCrimeMining
Law Crime Mining Based on Corpus build and content analysis by NLP methods. 基于领域语料库构建与NLP方法的裁判文书与犯罪案例文本挖掘项目
MedicalNamedEntityRecognition
Medical Named Entity Recognition implement using bi-directional lstm and crf model with char embedding.CCKS2017中文电子病例命名实体识别项目,主要实现使用了基于字向量的四层双向LSTM与CRF模型的网络.该项目提供了原始训练数据样本(一般醒目,出院情况,病史情况,病史特点,诊疗经过)与转换版本,训练脚本,预训练模型,可用于序列标注研究.把玩和PK使用.
oxford-nlp-practical1
Oxford Deep NLP 2017 course - Practical 1: word2vec
oxford-nlp-practical2
Oxford Deep NLP 2017 course - Practical 2: Text Classification
pytvzhen
最快油管英文视频转中文
Qwen
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
research_tao
NLP研究入门之道