rightyonghu commited on
Commit
efa471e
1 Parent(s): c18a9f2
Files changed (5) hide show
  1. README.md +2 -6
  2. config.json +19 -18
  3. flax_model.msgpack +0 -3
  4. pytorch_model.bin +2 -2
  5. tf_model.h5 +0 -3
README.md CHANGED
@@ -14,10 +14,6 @@ More detail: https://arxiv.org/abs/1907.12412
14
 
15
  ## Released Model Info
16
 
17
- |Model Name|Language|Model Structure|
18
- |:---:|:---:|:---:|
19
- |ernie-2.0-en| English |Layer:12, Hidden:768, Heads:12|
20
-
21
  This released pytorch model is converted from the officially released PaddlePaddle ERNIE model and
22
  a series of experiments have been conducted to check the accuracy of the conversion.
23
 
@@ -27,8 +23,8 @@ a series of experiments have been conducted to check the accuracy of the convers
27
  ## How to use
28
  ```Python
29
  from transformers import AutoTokenizer, AutoModel
30
- tokenizer = AutoTokenizer.from_pretrained("nghuyong/ernie-2.0-en")
31
- model = AutoModel.from_pretrained("nghuyong/ernie-2.0-en")
32
  ```
33
 
34
  ## Citation
 
14
 
15
  ## Released Model Info
16
 
 
 
 
 
17
  This released pytorch model is converted from the officially released PaddlePaddle ERNIE model and
18
  a series of experiments have been conducted to check the accuracy of the conversion.
19
 
 
23
  ## How to use
24
  ```Python
25
  from transformers import AutoTokenizer, AutoModel
26
+ tokenizer = AutoTokenizer.from_pretrained("nghuyong/ernie-2.0-base-en")
27
+ model = AutoModel.from_pretrained("nghuyong/ernie-2.0-base-en")
28
  ```
29
 
30
  ## Citation
config.json CHANGED
@@ -1,19 +1,20 @@
1
  {
2
- "attention_probs_dropout_prob": 0.1,
3
- "gradient_checkpointing": false,
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-05,
10
- "max_position_embeddings": 512,
11
- "model_type": "bert",
12
- "num_attention_heads": 12,
13
- "num_hidden_layers": 12,
14
- "pad_token_id": 0,
15
- "sent_type_vocab_size": 4,
16
- "task_type_vocab_size": 16,
17
- "type_vocab_size": 4,
18
- "vocab_size": 30522
19
- }
 
 
1
  {
2
+ "attention_probs_dropout_prob": 0.1,
3
+ "hidden_act": "gelu",
4
+ "hidden_dropout_prob": 0.1,
5
+ "hidden_size": 768,
6
+ "initializer_range": 0.02,
7
+ "max_position_embeddings": 512,
8
+ "num_attention_heads": 12,
9
+ "num_hidden_layers": 12,
10
+ "sent_type_vocab_size": 4,
11
+ "task_type_vocab_size": 16,
12
+ "vocab_size": 30522,
13
+ "layer_norm_eps": 1e-05,
14
+ "model_type": "bert",
15
+ "architectures": [
16
+ "BertModel"
17
+ ],
18
+ "type_vocab_size": 4,
19
+ "intermediate_size": 3072
20
+ }
flax_model.msgpack DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffcabfa5529fb2fea013bef416d2ab352044d0541c58906adfb4840e957be377
3
- size 437942253
 
 
 
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af27705a979a8c5ad867fca358b911297a823def39a2727dd7c7aaa855cdd49e
3
- size 440474579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b797c4dea488b04b589a1a44f4695208ee901c4a07114fd2adbe6f2b0935039
3
+ size 437998259
tf_model.h5 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc80a39d3be74ea21a8fc5ba7c8347c81f4c2775afd5ab0f87f503284c164f33
3
- size 536061752