sliderSun
commited on
Commit
•
91bd35b
1
Parent(s):
e7f2f6e
first commit
Browse files- README.md +30 -0
- config.json +39 -0
- pytorch_model.bin +3 -0
- vocab.txt +0 -0
README.md
CHANGED
@@ -1,3 +1,33 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
---
|
4 |
+
tags:
|
5 |
+
- bert
|
6 |
+
- NLU
|
7 |
+
- NLI
|
8 |
+
|
9 |
+
inference: true
|
10 |
+
|
11 |
+
widget:
|
12 |
+
- text: "湖北省黄冈市麻城市中国中部(麻城)石材循环经济产业园厦门路麻城盈泰环保科技有限公司[SEP]黄冈市麻城市中国中部石材循环经济产业园厦门路麻城盈泰环保科技有限公司"
|
13 |
+
|
14 |
+
---
|
15 |
+
# Erlangshen-Roberta-110M-POI, model (Chinese).
|
16 |
+
We add POI datasets, with a total of 5000000 samples. Our model is mainly based on [roberta](https://github.com/IDEA-CCNL/Erlangshen-Roberta-110M-Similarity)
|
17 |
+
|
18 |
+
## Usage
|
19 |
+
```python
|
20 |
+
from transformers import BertForSequenceClassification
|
21 |
+
from transformers import BertTokenizer
|
22 |
+
import torch
|
23 |
+
|
24 |
+
tokenizer=BertTokenizer.from_pretrained('swtx/Erlangshen-Roberta-110M-POI')
|
25 |
+
model=BertForSequenceClassification.from_pretrained('swtx/Erlangshen-Roberta-110M-POI')
|
26 |
+
|
27 |
+
texta='湖北省黄冈市麻城市中国中部(麻城)石材循环经济产业园厦门路麻城盈泰环保科技有限公司'
|
28 |
+
textb='黄冈市麻城市中国中部石材循环经济产业园厦门路麻城盈泰环保科技有限公司'
|
29 |
+
|
30 |
+
output=model(torch.tensor([tokenizer.encode(texta,textb)]))
|
31 |
+
print(torch.nn.functional.softmax(output.logits,dim=-1))
|
32 |
+
|
33 |
+
```
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "IDEA-CCNL/Erlangshen-Roberta-110M-Similarity",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"directionality": "bidi",
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "not similar",
|
16 |
+
"1": "similar"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"label2id": null,
|
21 |
+
"layer_norm_eps": 1e-12,
|
22 |
+
"max_position_embeddings": 512,
|
23 |
+
"model_type": "bert",
|
24 |
+
"num_attention_heads": 12,
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"output_past": true,
|
27 |
+
"pad_token_id": 1,
|
28 |
+
"pooler_fc_size": 768,
|
29 |
+
"pooler_num_attention_heads": 12,
|
30 |
+
"pooler_num_fc_layers": 3,
|
31 |
+
"pooler_size_per_head": 128,
|
32 |
+
"pooler_type": "first_token_transform",
|
33 |
+
"position_embedding_type": "absolute",
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.20.1",
|
36 |
+
"type_vocab_size": 2,
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 21128
|
39 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a069bb2ab2e28f461b2b4f37573734022665c46e597f6282821d45beb0558f86
|
3 |
+
size 409145207
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|