ganruyi
commited on
Commit
•
d8adcdd
1
Parent(s):
5eb6fcb
add zen2 base model
Browse files- config.json +22 -0
- ngram.txt +0 -0
- pytorch_model.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attention_probs_dropout_prob": 0.1,
|
| 3 |
+
"directionality": "bidi",
|
| 4 |
+
"hidden_act": "gelu",
|
| 5 |
+
"hidden_dropout_prob": 0.1,
|
| 6 |
+
"hidden_size": 768,
|
| 7 |
+
"initializer_range": 0.02,
|
| 8 |
+
"intermediate_size": 3072,
|
| 9 |
+
"layer_norm_eps": 1e-12,
|
| 10 |
+
"max_position_embeddings": 512,
|
| 11 |
+
"num_attention_heads": 12,
|
| 12 |
+
"num_hidden_layers": 12,
|
| 13 |
+
"num_hidden_word_layers": 6,
|
| 14 |
+
"pooler_fc_size": 768,
|
| 15 |
+
"pooler_num_attention_heads": 12,
|
| 16 |
+
"pooler_num_fc_layers": 3,
|
| 17 |
+
"pooler_size_per_head": 128,
|
| 18 |
+
"pooler_type": "first_token_transform",
|
| 19 |
+
"type_vocab_size": 2,
|
| 20 |
+
"vocab_size": 21128,
|
| 21 |
+
"word_size": 261361
|
| 22 |
+
}
|
ngram.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2af0a051c7980fe628362525c6f297dbbeebb3789deb9fd9023103ed851aa616
|
| 3 |
+
size 694398268
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|