feat: "Female", "Sports", "Literature", "Campus" 4 Classification Model。
Browse files- README.md +40 -0
- config.json +37 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: zh
|
3 |
+
tags:
|
4 |
+
- exbert
|
5 |
+
license: apache-2.0
|
6 |
+
widget:
|
7 |
+
- text: "女人做得越纯粹,皮肤和身材就越好"
|
8 |
+
- text: "我喜欢篮球"
|
9 |
+
---
|
10 |
+
|
11 |
+
# liam168/c4-zh-distilbert-base-uncased
|
12 |
+
|
13 |
+
## Model description
|
14 |
+
|
15 |
+
用 ["女性","体育","文学","校园"]4类数据训练的分类模型。
|
16 |
+
|
17 |
+
## Overview
|
18 |
+
|
19 |
+
- **Language model**: DistilBERT
|
20 |
+
- **Model size**: 280M
|
21 |
+
- **Language**: Chinese
|
22 |
+
|
23 |
+
## Example
|
24 |
+
|
25 |
+
```python
|
26 |
+
>>> from transformers import DistilBertForSequenceClassification , AutoTokenizer, pipeline
|
27 |
+
|
28 |
+
>>> model_name = "liam168/c4-zh-distilbert-base-uncased"
|
29 |
+
>>> class_num = 4
|
30 |
+
>>> ts_texts = ["女人做得越纯粹,皮肤和身材就越好", "我喜欢篮球"]
|
31 |
+
>>> model = DistilBertForSequenceClassification.from_pretrained(model_name, num_labels=class_num)
|
32 |
+
>>> tokenizer = AutoTokenizer.from_pretrained(model_name)
|
33 |
+
>>> classifier = pipeline('sentiment-analysis', model=model, tokenizer=tokenizer)
|
34 |
+
>>> classifier(ts_texts[0])
|
35 |
+
>>> classifier(ts_texts[1])
|
36 |
+
|
37 |
+
[{'label': 'Female', 'score': 0.9137857556343079}]
|
38 |
+
[{'label': 'Sports', 'score': 0.8206522464752197}]
|
39 |
+
|
40 |
+
```
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "Female",
|
13 |
+
"1": "Sports",
|
14 |
+
"2": "Literature",
|
15 |
+
"3": "Campus"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"label2id": {
|
19 |
+
"Female": 0,
|
20 |
+
"Sports": 1,
|
21 |
+
"Literature": 2,
|
22 |
+
"Campus": 3
|
23 |
+
},
|
24 |
+
"max_position_embeddings": 512,
|
25 |
+
"model_type": "distilbert",
|
26 |
+
"n_heads": 12,
|
27 |
+
"n_layers": 6,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"problem_type": "single_label_classification",
|
30 |
+
"qa_dropout": 0.1,
|
31 |
+
"seq_classif_dropout": 0.2,
|
32 |
+
"sinusoidal_pos_embds": false,
|
33 |
+
"tie_weights_": true,
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.9.0.dev0",
|
36 |
+
"vocab_size": 30522
|
37 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d599efd3f01521d7c4e278d0c6e8939cd2e882c595275d4e310f07a3039b4857
|
3 |
+
size 267866225
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|