conv bert medium small
Browse files- config.json +26 -0
- pytorch_model.bin +3 -0
- tf_model.h5 +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/abhishek/huggingface/models/convbert_models/convbert_medium_small",
|
3 |
+
"architectures": [
|
4 |
+
"ConvBertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"conv_kernel_size": 9,
|
9 |
+
"embedding_size": 128,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"head_ratio": 2,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_dropout_prob": 0.1,
|
14 |
+
"hidden_size": 384,
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 1536,
|
17 |
+
"layer_norm_eps": 1e-12,
|
18 |
+
"max_position_embeddings": 512,
|
19 |
+
"model_type": "conv_bert",
|
20 |
+
"num_attention_heads": 8,
|
21 |
+
"num_groups": 2,
|
22 |
+
"num_hidden_layers": 12,
|
23 |
+
"pad_token_id": 0,
|
24 |
+
"type_vocab_size": 2,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01b8f49a00d69b4d1cc28775c3850fb4b1c8b627867c9600d06484335490b84b
|
3 |
+
size 70022379
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a6d6af06729f5055ce722bb0fc8155174022681e3a68ae97bce619998a03b54
|
3 |
+
size 19459776
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|