LLM + 中文文本匹配 Chinese Question Matching Corpus
License: MIT License
' 
' 
四 支
茶對酒，賦對詩，燕子對鶯兒。栽花對種竹，落絮對遊絲。四目頡，一足夔，鴝鵒對鷺鷥。半池紅菡萏，一架白荼蘼。幾陣秋風能應候，一犁春雨甚知時。智伯恩深，國士吞變形之炭；羊公德大，邑人豎墮淚之碑。
行對止，速對遲，舞劍對圍棋。花箋對草字，竹簡對毛錐。汾水鼎，峴山碑，虎豹對熊羆。花開紅錦繡，水漾碧琉璃。去婦因探鄰舍棗，出妻爲種後園葵。笛韻和諧，仙管恰從雲裏降；櫓聲咿軋，漁舟正向雪中移。
戈對甲，鼓對旗，紫燕對黃鸝。梅酸對李苦，青眼對白眉。三弄笛，一圍棋，雨打對風吹。海棠春睡早，楊柳晝眠遲。張駿曾爲槐樹賦，杜陵不作海棠詩。晉士特奇，可比一斑之豹；唐儒博識，堪爲五總之龜。
本项目开源 ERNIE 3.0 Base 、ERNIE 3.0 Medium 、 ERNIE 3.0 Mini 、 ERNIE 3.0 Micro 、 ERNIE 3.0 Nano 五个模型：
ERNIE 3.0-Base (12-layer, 768-hidden, 12-heads)
ERNIE 3.0-Medium (6-layer, 768-hidden, 12-heads)
ERNIE 3.0-Mini (6-layer, 384-hidden, 12-heads)
ERNIE 3.0-Micro (4-layer, 384-hidden, 12-heads)
ERNIE 3.0-Nano (4-layer, 312-hidden, 12-heads)
https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/ernie-3.0
[2023-03-15 05:04:26,525] [ INFO] - tokenizer config file saved in ../user_data/model_data/tokenizer_config.json
[2023-03-15 05:04:26,525] [ INFO] - Special tokens file saved in ../user_data/model_data/special_tokens_map.json
Step 758210, Epoch: 51, Batch: 14460, Loss: 0.0018, ACC: 0.9925, P: 0.9947, R: 0.9895, F1: 0.9921, Speed: 0.34 it/s
Step 758220, Epoch: 51, Batch: 14470, Loss: 0.0047, ACC: 0.9950, P: 0.9958, R: 0.9931, F1: 0.9945, Speed: 1.22 it/s
Step 758230, Epoch: 51, Batch: 14480, Loss: 0.0026, ACC: 0.9950, P: 0.9935, R: 0.9954, F1: 0.9945, Speed: 1.27 it/s
Step 758240, Epoch: 51, Batch: 14490, Loss: 0.0009, ACC: 0.9947, P: 0.9929, R: 0.9950, F1: 0.9940, Speed: 1.23 it/s
Step 758250, Epoch: 51, Batch: 14500, Loss: 0.0175, ACC: 0.9950, P: 0.9938, R: 0.9950, F1: 0.9944, Speed: 1.29 it/s
Step 758260, Epoch: 51, Batch: 14510, Loss: 0.0094, ACC: 0.9946, P: 0.9926, R: 0.9954, F1: 0.9940, Speed: 1.29 it/s
Step 758270, Epoch: 51, Batch: 14520, Loss: 0.0012, ACC: 0.9946, P: 0.9929, R: 0.9953, F1: 0.9941, Speed: 1.27 it/s
Step 758280, Epoch: 51, Batch: 14530, Loss: 0.0092, ACC: 0.9942, P: 0.9917, R: 0.9955, F1: 0.9936, Speed: 1.20 it/s
Step 758290, Epoch: 51, Batch: 14540, Loss: 0.0011, ACC: 0.9943, P: 0.9923, R: 0.9951, F1: 0.9937, Speed: 1.29 it/s
Step 758300, Epoch: 51, Batch: 14550, Loss: 0.0158, ACC: 0.9941, P: 0.9920, R: 0.9950, F1: 0.9935, Speed: 1.31 it/s
Step 758310, Epoch: 51, Batch: 14560, Loss: 0.0003, ACC: 0.9943, P: 0.9922, R: 0.9952, F1: 0.9937, Speed: 1.25 it/s
Step 758320, Epoch: 51, Batch: 14570, Loss: 0.0033, ACC: 0.9946, P: 0.9928, R: 0.9951, F1: 0.9940, Speed: 1.20 it/s
Step 758330, Epoch: 51, Batch: 14580, Loss: 0.0314, ACC: 0.9943, P: 0.9923, R: 0.9951, F1: 0.9937, Speed: 1.22 it/s
^CLAUNCH INFO 2023-03-15 05:06:17,693 Terminating with signal 2
LAUNCH INFO 2023-03-15 05:06:17,894 Exit with signal 2
real 11538m41.608s
user 7613m5.520s
sys 4269m59.764s
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft
Open source projects and samples from Microsoft.
Google
Google ❤️ Open Source for everyone.
Alibaba
Alibaba Open Source for everyone
D3
Data-Driven Documents codes.
Tencent
China tencent open source team.