hummingbird
/
fastNLP
Not watched
2
0
Fork 0
Code
Releases 13 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
1314 Commits
3 Branches
25 MB
0 Download
 
 
 
 
 
Tree: b3718b10dc
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'b3718b10dc'
${ noResults }
fastNLP/test
Yige Xu b3718b10dc 1. rename init_embed to embed in models/*; 2. update documents in models/bert.py; 3. update tutorial six. 5 years ago
..
core 1.当前支持的encoding_type都支持从tag_vocab中自动判断;避免触发无意识导致的metric bug; 2. 修复部分inplace操作无法求导的问题; 3.Vocabulary将一些属性通过property暴露 5 years ago
data_for_tests add testing codes and data for loader and pipe. 5 years ago
embeddings 1. update bert.py and fix a bug in bert_embedding to adapt torch 1.2.0; 2. update models/bert.py and add BertForSentenceMatching model, now a BertEmbedding param should be passed to these five models; 3. create a small bert version for testing and modify test/models/test_bert.py; 4. move small glove and word2vec files to data_for_tests/embedding/small_static_embedding dir and fix relevant test codes; 5. delete some __init__.py files in test dir. 5 years ago
io add testing codes and data for loader and pipe. 5 years ago
models 1. rename init_embed to embed in models/*; 2. update documents in models/bert.py; 3. update tutorial six. 5 years ago
modules 1.当前支持的encoding_type都支持从tag_vocab中自动判断;避免触发无意识导致的metric bug; 2. 修复部分inplace操作无法求导的问题; 3.Vocabulary将一些属性通过property暴露 5 years ago
__init__.py fix some bugs in test code. 5 years ago
test_tutorials.py 1.修复部分测试; 2.修复StaticEmbedding中未找到词初始化bug 5 years ago
Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

一款轻量级的自然语言处理（NLP）工具包，目标是减少用户项目中的工程型代码，例如数据处理循环、训练循环、多卡运行等

Python Jupyter Notebook Text CSV Markdown