push models tf/pytorch for qarib60_860k
Browse files- .gitattributes +2 -0
- bert_config.json +20 -0
- config.json +20 -0
- model.ckpt-860000.data-00000-of-00001 +3 -0
- model.ckpt-860000.index +0 -0
- model.ckpt-860000.meta +0 -0
- pytorch_model.bin +3 -0
- vocab.txt +0 -0
.gitattributes
CHANGED
|
@@ -6,3 +6,5 @@
|
|
| 6 |
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 8 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 6 |
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 8 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
model.ckpt-860000.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
|
bert_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "bert",
|
| 3 |
+
"attention_probs_dropout_prob": 0.1,
|
| 4 |
+
"directionality": "bidi",
|
| 5 |
+
"hidden_act": "gelu",
|
| 6 |
+
"hidden_dropout_prob": 0.1,
|
| 7 |
+
"hidden_size": 768,
|
| 8 |
+
"initializer_range": 0.02,
|
| 9 |
+
"intermediate_size": 3072,
|
| 10 |
+
"max_position_embeddings": 512,
|
| 11 |
+
"num_attention_heads": 12,
|
| 12 |
+
"num_hidden_layers": 12,
|
| 13 |
+
"pooler_fc_size": 768,
|
| 14 |
+
"pooler_num_attention_heads": 12,
|
| 15 |
+
"pooler_num_fc_layers": 3,
|
| 16 |
+
"pooler_size_per_head": 128,
|
| 17 |
+
"pooler_type": "first_token_transform",
|
| 18 |
+
"type_vocab_size": 2,
|
| 19 |
+
"vocab_size": 64000
|
| 20 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "bert",
|
| 3 |
+
"attention_probs_dropout_prob": 0.1,
|
| 4 |
+
"directionality": "bidi",
|
| 5 |
+
"hidden_act": "gelu",
|
| 6 |
+
"hidden_dropout_prob": 0.1,
|
| 7 |
+
"hidden_size": 768,
|
| 8 |
+
"initializer_range": 0.02,
|
| 9 |
+
"intermediate_size": 3072,
|
| 10 |
+
"max_position_embeddings": 512,
|
| 11 |
+
"num_attention_heads": 12,
|
| 12 |
+
"num_hidden_layers": 12,
|
| 13 |
+
"pooler_fc_size": 768,
|
| 14 |
+
"pooler_num_attention_heads": 12,
|
| 15 |
+
"pooler_num_fc_layers": 3,
|
| 16 |
+
"pooler_size_per_head": 128,
|
| 17 |
+
"pooler_type": "first_token_transform",
|
| 18 |
+
"type_vocab_size": 2,
|
| 19 |
+
"vocab_size": 64000
|
| 20 |
+
}
|
model.ckpt-860000.data-00000-of-00001
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c504a4845373181d8addb5c9296e068c60450d7b6ea1493d4951dc0a53211503
|
| 3 |
+
size 1630212128
|
model.ckpt-860000.index
ADDED
|
Binary file (9.39 kB). View file
|
|
|
model.ckpt-860000.meta
ADDED
|
Binary file (4.67 MB). View file
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec26fc1a44e6bf3db8846f0d99e4a63a1ded62b4a86cc03dbd81136259fec814
|
| 3 |
+
size 543452854
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|