Upload folder using huggingface_hub
Browse files- config.json +17 -20
- pytorch_model.bin +2 -2
- special_tokens_map.json +5 -13
- tokenizer.json +0 -0
- tokenizer_config.json +8 -11
- vocab.txt +0 -0
config.json
CHANGED
@@ -1,28 +1,25 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/tmp/
|
|
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"hidden_act": "gelu",
|
11 |
-
"hidden_dropout_prob": 0.1,
|
12 |
-
"hidden_size": 768,
|
13 |
"initializer_range": 0.02,
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
18 |
-
"
|
19 |
-
"num_hidden_layers": 12,
|
20 |
-
"pad_token_id": 1,
|
21 |
-
"position_embedding_type": "absolute",
|
22 |
"problem_type": "single_label_classification",
|
|
|
|
|
|
|
|
|
23 |
"torch_dtype": "float32",
|
24 |
"transformers_version": "4.31.0",
|
25 |
-
"
|
26 |
-
"use_cache": true,
|
27 |
-
"vocab_size": 50265
|
28 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/tmp/tmp_cdqlsaj",
|
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 |
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
|
|
|
|
|
|
17 |
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
"torch_dtype": "float32",
|
23 |
"transformers_version": "4.31.0",
|
24 |
+
"vocab_size": 30522
|
|
|
|
|
25 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab03e4c558884a1fb9bd4bb65f451eb94d53338da61b7a78800772416cf70738
|
3 |
+
size 267854570
|
special_tokens_map.json
CHANGED
@@ -1,15 +1,7 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
|
7 |
-
"lstrip": true,
|
8 |
-
"normalized": false,
|
9 |
-
"rstrip": false,
|
10 |
-
"single_word": false
|
11 |
-
},
|
12 |
-
"pad_token": "<pad>",
|
13 |
-
"sep_token": "</s>",
|
14 |
-
"unk_token": "<unk>"
|
15 |
}
|
|
|
1 |
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,16 +1,13 @@
|
|
1 |
{
|
2 |
-
"add_prefix_space": false,
|
3 |
-
"bos_token": "<s>",
|
4 |
"clean_up_tokenization_spaces": true,
|
5 |
-
"cls_token": "
|
6 |
"do_lower_case": true,
|
7 |
-
"
|
8 |
-
"errors": "replace",
|
9 |
-
"mask_token": "<mask>",
|
10 |
"model_max_length": 512,
|
11 |
-
"pad_token": "
|
12 |
-
"sep_token": "
|
13 |
-
"
|
14 |
-
"
|
15 |
-
"
|
|
|
16 |
}
|
|
|
1 |
{
|
|
|
|
|
2 |
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
|
|
|
|
6 |
"model_max_length": 512,
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"strip_accents": null,
|
10 |
+
"tokenize_chinese_chars": true,
|
11 |
+
"tokenizer_class": "DistilBertTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|