David Pollack
commited on
Commit
•
2fd2e4b
1
Parent(s):
52f76b2
dummy sequence classification model for testing
Browse files- README.md +13 -0
- config.json +26 -0
- pytorch_model.bin +0 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
This is a dummy model that can be used for testing.
|
2 |
+
|
3 |
+
It was created as follows in a python shell
|
4 |
+
|
5 |
+
```python
|
6 |
+
import transformers
|
7 |
+
config = transformers.DistilBertConfig(vocab_size=1, n_layers=1, n_heads=1, dim=1, hidden_dim=4 * 1, num_labels=2, id2label={0: "negative", 1: "positive"}, label2id={"negative": 0, "positive": 1})
|
8 |
+
model = transformers.DistilBertForSequenceClassification(config)
|
9 |
+
tokenizer = transformers.DistilBertTokenizer("/tmp/empty_vocab.txt", model_max_length=512)
|
10 |
+
config.save_pretrained(".")
|
11 |
+
model.save_pretrained(".")
|
12 |
+
tokenizer.save_pretrained(".")
|
13 |
+
```
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation": "gelu",
|
3 |
+
"attention_dropout": 0.1,
|
4 |
+
"dim": 1,
|
5 |
+
"dropout": 0.1,
|
6 |
+
"hidden_dim": 4,
|
7 |
+
"id2label": {
|
8 |
+
"0": "negative",
|
9 |
+
"1": "positive"
|
10 |
+
},
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"label2id": {
|
13 |
+
"negative": 0,
|
14 |
+
"positive": 1
|
15 |
+
},
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model_type": "distilbert",
|
18 |
+
"n_heads": 1,
|
19 |
+
"n_layers": 1,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"qa_dropout": 0.1,
|
22 |
+
"seq_classif_dropout": 0.2,
|
23 |
+
"sinusoidal_pos_embds": false,
|
24 |
+
"transformers_version": "4.4.2",
|
25 |
+
"vocab_size": 1
|
26 |
+
}
|
pytorch_model.bin
ADDED
Binary file (11.3 kB). View file
|
|
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_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "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}
|
vocab.txt
ADDED
File without changes
|