TusharGoel
commited on
Commit
•
63129df
1
Parent(s):
c211d20
Upload 8 files
Browse files- added_tokens.json +7 -0
- config.json +29 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +78 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 2,
|
3 |
+
"<mask>": 50264,
|
4 |
+
"<pad>": 1,
|
5 |
+
"<s>": 0,
|
6 |
+
"<unk>": 3
|
7 |
+
}
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "SCUT-DLVCLab/lilt-roberta-en-base",
|
3 |
+
"architectures": [
|
4 |
+
"LiltForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"channel_shrink_ratio": 4,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"max_2d_position_embeddings": 1024,
|
18 |
+
"max_position_embeddings": 514,
|
19 |
+
"model_type": "lilt",
|
20 |
+
"num_attention_heads": 12,
|
21 |
+
"num_hidden_layers": 12,
|
22 |
+
"pad_token_id": 1,
|
23 |
+
"position_embedding_type": "absolute",
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.34.0",
|
26 |
+
"type_vocab_size": 1,
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 50265
|
29 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af19cb0323181b284410f1a59cdcac62819016be9732a0f20c419a6488310f8e
|
3 |
+
size 520801357
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": "<mask>",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sep_token": "</s>",
|
8 |
+
"unk_token": "<unk>"
|
9 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"additional_special_tokens": [],
|
46 |
+
"bos_token": "<s>",
|
47 |
+
"clean_up_tokenization_spaces": true,
|
48 |
+
"cls_token": "<s>",
|
49 |
+
"cls_token_box": [
|
50 |
+
0,
|
51 |
+
0,
|
52 |
+
0,
|
53 |
+
0
|
54 |
+
],
|
55 |
+
"eos_token": "</s>",
|
56 |
+
"errors": "replace",
|
57 |
+
"mask_token": "<mask>",
|
58 |
+
"model_max_length": 512,
|
59 |
+
"only_label_first_subword": true,
|
60 |
+
"pad_token": "<pad>",
|
61 |
+
"pad_token_box": [
|
62 |
+
0,
|
63 |
+
0,
|
64 |
+
0,
|
65 |
+
0
|
66 |
+
],
|
67 |
+
"pad_token_label": -100,
|
68 |
+
"sep_token": "</s>",
|
69 |
+
"sep_token_box": [
|
70 |
+
0,
|
71 |
+
0,
|
72 |
+
0,
|
73 |
+
0
|
74 |
+
],
|
75 |
+
"tokenizer_class": "LayoutLMv3Tokenizer",
|
76 |
+
"trim_offsets": true,
|
77 |
+
"unk_token": "<unk>"
|
78 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|