rightyonghu commited on
Commit
8a7f559
•
1 Parent(s): b06176b
Files changed (5) hide show
  1. README.md +2 -6
  2. config.json +13 -16
  3. flax_model.msgpack +0 -3
  4. pytorch_model.bin +2 -2
  5. tf_model.h5 +0 -3
README.md CHANGED
@@ -15,10 +15,6 @@ More detail: https://arxiv.org/abs/1904.09223
15
 
16
  ## Released Model Info
17
 
18
- |Model Name|Language|Model Structure|
19
- |:---:|:---:|:---:|
20
- |ernie-1.0| Chinese |Layer:12, Hidden:768, Heads:12|
21
-
22
  This released pytorch model is converted from the officially released PaddlePaddle ERNIE model and
23
  a series of experiments have been conducted to check the accuracy of the conversion.
24
 
@@ -28,8 +24,8 @@ a series of experiments have been conducted to check the accuracy of the convers
28
  ## How to use
29
  ```Python
30
  from transformers import AutoTokenizer, AutoModel
31
- tokenizer = AutoTokenizer.from_pretrained("nghuyong/ernie-1.0")
32
- model = AutoModel.from_pretrained("nghuyong/ernie-1.0")
33
  ```
34
 
35
  ## Citation
 
15
 
16
  ## Released Model Info
17
 
 
 
 
 
18
  This released pytorch model is converted from the officially released PaddlePaddle ERNIE model and
19
  a series of experiments have been conducted to check the accuracy of the conversion.
20
 
 
24
  ## How to use
25
  ```Python
26
  from transformers import AutoTokenizer, AutoModel
27
+ tokenizer = AutoTokenizer.from_pretrained("nghuyong/ernie-1.0-base-zh")
28
+ model = AutoModel.from_pretrained("nghuyong/ernie-1.0-base-zh")
29
  ```
30
 
31
  ## Citation
config.json CHANGED
@@ -1,17 +1,14 @@
1
  {
2
- "attention_probs_dropout_prob": 0.1,
3
- "gradient_checkpointing": false,
4
- "hidden_act": "relu",
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": 513,
11
- "model_type": "bert",
12
- "num_attention_heads": 12,
13
- "num_hidden_layers": 12,
14
- "pad_token_id": 0,
15
- "type_vocab_size": 2,
16
- "vocab_size": 18000
17
- }
 
1
  {
2
+ "attention_probs_dropout_prob": 0.1,
3
+ "hidden_act": "relu",
4
+ "hidden_dropout_prob": 0.1,
5
+ "hidden_size": 768,
6
+ "initializer_range": 0.02,
7
+ "max_position_embeddings": 513,
8
+ "num_attention_heads": 12,
9
+ "num_hidden_layers": 12,
10
+ "type_vocab_size": 2,
11
+ "vocab_size": 18000,
12
+ "layer_norm_eps": 1e-05,
13
+ "intermediate_size": 3072
14
+ }
 
 
 
flax_model.msgpack DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b33fa3eeb4a85a316b9a99e54a6c1f4a99eb8cc6c9061f9a38ea6900ad5cf20b
3
- size 399471597
 
 
 
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3bff01e42d7b62527ba2d4823159c70e3402ac3798434f51f05166a0df2e65e
3
- size 401953835
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a973c80196dbb793c34ac0734b8c09550beac857c303f0b012124752b0008585
3
+ size 401969705
tf_model.h5 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:658d7ba83b7daba99d11c4f8e3a78f37b4f96fa2d08865a24ca492a1348899c4
3
- size 459070352