small commit
Browse files- README.md +1 -0
- config.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
a large chinese bert trained from wiki and news.
|
config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"attention_probs_dropout_prob": 0.1, "directionality": "bidi", "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 4096, "max_position_embeddings": 512, "num_attention_heads": 16, "num_hidden_layers": 24, "type_vocab_size": 2, "vocab_size": 21128}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_lower_case": false
|
3 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|