paineliu Goto Github PK

anydoc

awesome-text2sql

Curated tutorials and resources for Large Language Models, Text2SQL, Text2DSL、Text2API、Text2Vis and more.

bcc-nlq

bert-chinese-text-classification-pytorch

使用Bert，ERNIE，进行中文文本分类

bert-intent-slot-detector

BERT-based intent and slots detector for chatbots.

bert_vits_chinese

Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support ONNX streaming out!

bertclassifier

基于PyTorch的BERT中文文本分类模型（BERT Chinese text classification model implemented by PyTorch）

bertclassify

文本分类

camels

多粒度分词的CQL解析器系统(CQL Analyzer with Multi-lEvel Lexical System, CAMELS)

ccse

Instance Segmentation for Chinese Character Stroke Extraction, Datasets and Benchmarks.

ccsem

chaizi

GBK汉字拆分表

chatglm3-finetuning

chatlm-mini-chinese

中文对话0.2B小模型（ChatLM-Chinese-0.2B），开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调，给出三元组信息抽取微调示例。

chinese-fastspeech2

基于标贝数据继续训练，同时对原本的FastSpeech2模型做了改进，引入了韵律表征以及韵律预测模块，使中文发音更生动且富有节奏

chinese-poetry

The most comprehensive database of Chinese poetry 🧶最全中华古诗词数据库, 唐宋两朝近一万四千古诗人, 接近5.5万首唐诗加26万宋诗. 两宋时期1564位词人，21050首词。

cnchar

🇨🇳 功能全面的汉字工具库 (拼音 笔画 偏旁 成语 语音 可视化等) (Chinese character util)

cqlparser

Corpus Query Language Parser

cqls

Parse Corpus Query Language (CQL) into a list of JSON queries

db-gpt-hub

A repository that contains models, datasets, and fine-tuning techniques for DB-GPT, with the purpose of enhancing model performance in Text-to-SQL

dink

dolma

Data and tools for generating and inspecting OLMo pre-training data.

few-shot-nl2sql-with-prompting

gpt2-chinese

Chinese version of GPT2 training code, using BERT tokenizer.

han_comp_split

Extraction of Chinese Character Components in Digital Ink based on Recognition Scores

jointbert-zh

Pytorch implementation of JointBERT: "BERT for Joint Intent Classification and Slot Filling"

jointidsf

BERT-based joint intent detection and slot filling with intent-slot attention mechanism (INTERSPEECH 2021)

llms-from-scratch-cn

仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理

mingpt

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

nanogpt

The simplest, fastest repository for training/finetuning medium-sized GPTs.