yongzhuo repositories

ChatGLM2-6B微调, SFT/LoRA, instruction finetune

Last commit Jul 19, 2023

chatglm3-6b, 微调/LORA/推理/单机多卡/deepspeed/支持多轮对话

Last commit Nov 30, 2023

A concept and obvious expression pattern collection of Chinese compound event extraction which then be evolved into ComplexEventGraph，本项目提出了中文复合事件的概念与显式模式，包括条件事件、因果事件、顺承事件、反转事件等事件抽取，并形成事理图谱。

Last commit Dec 15, 2018

InternLM-7B微调, SFT/LoRA, instruction finetune

Last commit May 17, 2024

Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for text-labeling and text-classification, includes Word2Vec, BERT, and GPT2 Language Embedding.

Last commit Jul 5, 2020

中文长文本分类、短句子分类、多标签分类、两句子相似度（Chinese Text Classification of Keras NLP, multi-label classify, or sentence classify, long or short），字词句向量嵌入层（embeddings）和网络层（graph）构建基类，FastText，TextCNN，CharCNN，TextRNN, RCNN, DCNN, DPCNN, VDCNN, CRNN, Bert, Xlnet, Albert, Attention, DeepMoji, HAN, 胶囊网络-CapsuleNet, Transformer-encode, Seq2seq, SWEM, LEAM, TextGCN

Last commit Dec 5, 2023

中文大模型微调(LLM-SFT), 数学指令数据集MWP-Instruct, 支持模型(ChatGLM-6B, LLaMA, Bloom-7B, baichuan-7B), 支持(LoRA, QLoRA, DeepSpeed, UI, TensorboardX), 支持(微调, 推理, 测评, 接口)等.

Last commit May 17, 2024

LlaMA3-SFT, Meta-Llama-3-8B/Meta-Llama-3-8B-Instruct微调(transformers)/LORA(peft)/推理, 支持中文(chinese, zh)

Last commit May 17, 2024

Llama2-SFT, Llama-2-7B微调(transformers)/LORA(peft)/推理

Last commit Jul 26, 2023

Macadam是一个以Tensorflow(Keras)和bert4keras为基础，专注于文本分类、序列标注和关系抽取的自然语言处理工具包。支持RANDOM、WORD2VEC、FASTTEXT、BERT、ALBERT、ROBERTA、NEZHA、XLNET、ELECTRA、GPT-2等EMBEDDING嵌入; 支持FineTune、FastText、TextCNN、CharCNN、BiRNN、RCNN、DCNN、CRNN、DeepMoji、SelfAttention、HAN、Capsule等文本分类算法; 支持CRF、Bi-LSTM-CRF、CNN-LSTM、DGCNN、Bi-LSTM-LAN、Lattice-LSTM-Batch、MRC等序列标注算法。

Last commit Jul 15, 2020

macrogpt大模型全量预训练(1b3,32层), 多卡deepspeed/单卡adafactor

Last commit Nov 30, 2023

自然语言处理工具Macropodus，基于Albert+BiLSTM+CRF深度学习网络架构，中文分词，词性标注，命名实体识别，新词发现，关键词，文本摘要，文本相似度，科学计算器，中文数字阿拉伯数字(罗马数字)转换，中文繁简转换，拼音转换。tookit(tool) of NLP，CWS(chinese word segnment)，POS(Part-Of-Speech Tagging)，NER(name entity recognition)，Find(new words discovery)，Keyword(keyword extraction)，Summarize(text summarization)，Sim(text similarity)，Calculate(scientific calculator)，Chi2num(chinese number to arabic number)

Last commit Dec 25, 2020

中文开放信息抽取系统, open-information-extraction-system, build open-knowledge-graph(SPO, subject-predicate-object) by pyltp(version==3.4.0)

Last commit Aug 2, 2021

中文文本分类、序列标注工具包（pytorch），支持中文长文本、短文本的多类、多标签分类任务，支持中文命名实体识别、词性标注、分词、抽取式文本摘要等序列标注任务。 Chinese text classification and sequence labeling toolkit, supports multi class and multi label classification, text similsrity, text summary and NER.

Last commit Jul 18, 2024

阿里通义千问(Qwen-7B-Chat/Qwen-7B), 微调/LORA/推理

Last commit May 17, 2024

阿里通义千问(Qwen3.5-9B/4B/2B/0.8B/27B/35B/122B/397B), LoRA, SFT

Last commit Apr 11, 2026

文本数据分析, Text-Analysis

Last commit Nov 1, 2021

tensorflow-transformer(tft) of pre-processing and post-processing of text-classification

Last commit Mar 16, 2020

Tookit-Sihui, a tool of some common algorithm, AI文本混合科学计算器(calculator-sihui), 句子词频-逆文本频率(TF-IDF),搜索BM25, 前缀树搜索关键词(trietree), 模板匹配-递归函数(func_recursive)，中文数字转阿拉伯数字(chinese to number)，阿拉伯数字转汉语数字， HMM, CRF

Last commit Apr 9, 2021

构建中文词频词典-搜索引擎式切词（create chinese word dict of freq by segnment of search）

Last commit Dec 17, 2019