ybakman
commited on
Commit
•
ff1106e
1
Parent(s):
b27f3de
model upload
Browse files- added_tokens.json +10 -0
- config.json +44 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +73 -0
- tokenizer.json +0 -0
- tokenizer_config.json +131 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[prob_token_0]": 50265,
|
3 |
+
"[prob_token_1]": 50266,
|
4 |
+
"[prob_token_2]": 50267,
|
5 |
+
"[prob_token_3]": 50268,
|
6 |
+
"[prob_token_4]": 50269,
|
7 |
+
"[prob_token_5]": 50270,
|
8 |
+
"[prob_token_6]": 50271,
|
9 |
+
"[prob_token_7]": 50272
|
10 |
+
}
|
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"edges": [
|
10 |
+
9.088523711398011e-08,
|
11 |
+
0.4886343777179718,
|
12 |
+
0.8423471450805664,
|
13 |
+
0.9731593132019043,
|
14 |
+
0.9975177049636841,
|
15 |
+
0.9998431205749512,
|
16 |
+
0.9999911785125732,
|
17 |
+
1.0
|
18 |
+
],
|
19 |
+
"eos_token_id": 2,
|
20 |
+
"hidden_act": "gelu",
|
21 |
+
"hidden_dropout_prob": 0.1,
|
22 |
+
"hidden_size": 768,
|
23 |
+
"id2label": {
|
24 |
+
"0": "LABEL_0"
|
25 |
+
},
|
26 |
+
"initializer_range": 0.02,
|
27 |
+
"intermediate_size": 3072,
|
28 |
+
"label2id": {
|
29 |
+
"LABEL_0": 0
|
30 |
+
},
|
31 |
+
"layer_norm_eps": 1e-05,
|
32 |
+
"max_position_embeddings": 514,
|
33 |
+
"model_type": "roberta",
|
34 |
+
"num_attention_heads": 12,
|
35 |
+
"num_hidden_layers": 12,
|
36 |
+
"number_of_bins": 8,
|
37 |
+
"pad_token_id": 1,
|
38 |
+
"position_embedding_type": "absolute",
|
39 |
+
"torch_dtype": "float32",
|
40 |
+
"transformers_version": "4.41.1",
|
41 |
+
"type_vocab_size": 1,
|
42 |
+
"use_cache": true,
|
43 |
+
"vocab_size": 50273
|
44 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31992698780811db123689a20087829f6127019f6646d69e5b8cf1ff5089f7f0
|
3 |
+
size 498634324
|
special_tokens_map.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "[prob_token_0]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "[prob_token_1]",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"content": "[prob_token_2]",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"content": "[prob_token_3]",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"content": "[prob_token_4]",
|
33 |
+
"lstrip": false,
|
34 |
+
"normalized": false,
|
35 |
+
"rstrip": false,
|
36 |
+
"single_word": false
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"content": "[prob_token_5]",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"content": "[prob_token_6]",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"content": "[prob_token_7]",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false
|
58 |
+
}
|
59 |
+
],
|
60 |
+
"bos_token": "<s>",
|
61 |
+
"cls_token": "<s>",
|
62 |
+
"eos_token": "</s>",
|
63 |
+
"mask_token": {
|
64 |
+
"content": "<mask>",
|
65 |
+
"lstrip": true,
|
66 |
+
"normalized": false,
|
67 |
+
"rstrip": false,
|
68 |
+
"single_word": false
|
69 |
+
},
|
70 |
+
"pad_token": "<pad>",
|
71 |
+
"sep_token": "</s>",
|
72 |
+
"unk_token": "<unk>"
|
73 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,131 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
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": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"50265": {
|
45 |
+
"content": "[prob_token_0]",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"50266": {
|
53 |
+
"content": "[prob_token_1]",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"50267": {
|
61 |
+
"content": "[prob_token_2]",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"50268": {
|
69 |
+
"content": "[prob_token_3]",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"50269": {
|
77 |
+
"content": "[prob_token_4]",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"50270": {
|
85 |
+
"content": "[prob_token_5]",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"50271": {
|
93 |
+
"content": "[prob_token_6]",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
},
|
100 |
+
"50272": {
|
101 |
+
"content": "[prob_token_7]",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": true
|
107 |
+
}
|
108 |
+
},
|
109 |
+
"additional_special_tokens": [
|
110 |
+
"[prob_token_0]",
|
111 |
+
"[prob_token_1]",
|
112 |
+
"[prob_token_2]",
|
113 |
+
"[prob_token_3]",
|
114 |
+
"[prob_token_4]",
|
115 |
+
"[prob_token_5]",
|
116 |
+
"[prob_token_6]",
|
117 |
+
"[prob_token_7]"
|
118 |
+
],
|
119 |
+
"bos_token": "<s>",
|
120 |
+
"clean_up_tokenization_spaces": true,
|
121 |
+
"cls_token": "<s>",
|
122 |
+
"eos_token": "</s>",
|
123 |
+
"errors": "replace",
|
124 |
+
"mask_token": "<mask>",
|
125 |
+
"model_max_length": 512,
|
126 |
+
"pad_token": "<pad>",
|
127 |
+
"sep_token": "</s>",
|
128 |
+
"tokenizer_class": "RobertaTokenizer",
|
129 |
+
"trim_offsets": true,
|
130 |
+
"unk_token": "<unk>"
|
131 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|