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.
1408 Commits
3 Branches
25 MB
739 Download
Tree: d0a2b032bd
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'd0a2b032bd'
${ noResults }
fastNLP/test/data_for_tests/embedding/small_bert/config.json

config.json 303 B
Raw Normal View History

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.
6 years ago
​
​
​
​
​
​
​
​
​
​
​
​
 12345678910111213 
  1. {

  2.   "attention_probs_dropout_prob": 0.1,

  3.   "hidden_act": "gelu",

  4.   "hidden_dropout_prob": 0.1,

  5.   "hidden_size": 16,

  6.   "initializer_range": 0.02,

  7.   "intermediate_size": 64,

  8.   "max_position_embeddings": 32,

  9.   "num_attention_heads": 4,

  10.   "num_hidden_layers": 2,

  11.   "type_vocab_size": 2,

  12.   "vocab_size": 20

  13. }

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