Update model and tokenizer file
Browse files- config.json +8 -6
- pytorch_model.bin +2 -2
- special_tokens_map.json +5 -1
- tokenizer.json +101 -14
- tokenizer_config.json +5 -0
config.json
CHANGED
@@ -1,8 +1,9 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/home/kibrq/
|
3 |
"architectures": [
|
4 |
"EncoderDecoderModel"
|
5 |
],
|
|
|
6 |
"decoder": {
|
7 |
"_name_or_path": "",
|
8 |
"add_cross_attention": true,
|
@@ -53,7 +54,7 @@
|
|
53 |
"output_attentions": false,
|
54 |
"output_hidden_states": false,
|
55 |
"output_scores": false,
|
56 |
-
"pad_token_id":
|
57 |
"position_embedding_type": "absolute",
|
58 |
"prefix": null,
|
59 |
"problem_type": null,
|
@@ -78,7 +79,7 @@
|
|
78 |
"typical_p": 1.0,
|
79 |
"use_bfloat16": false,
|
80 |
"use_cache": true,
|
81 |
-
"vocab_size":
|
82 |
},
|
83 |
"decoder_start_token_id": 11,
|
84 |
"encoder": {
|
@@ -131,7 +132,7 @@
|
|
131 |
"output_attentions": false,
|
132 |
"output_hidden_states": false,
|
133 |
"output_scores": false,
|
134 |
-
"pad_token_id":
|
135 |
"position_embedding_type": "absolute",
|
136 |
"prefix": null,
|
137 |
"problem_type": null,
|
@@ -156,11 +157,12 @@
|
|
156 |
"typical_p": 1.0,
|
157 |
"use_bfloat16": false,
|
158 |
"use_cache": true,
|
159 |
-
"vocab_size":
|
160 |
},
|
|
|
161 |
"is_encoder_decoder": true,
|
162 |
"model_type": "encoder-decoder",
|
163 |
-
"pad_token_id":
|
164 |
"torch_dtype": "float32",
|
165 |
"transformers_version": null
|
166 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/home/kibrq/draft/commutator-translator/bert-bert-512/checkpoint-419000",
|
3 |
"architectures": [
|
4 |
"EncoderDecoderModel"
|
5 |
],
|
6 |
+
"bos_token_id": 11,
|
7 |
"decoder": {
|
8 |
"_name_or_path": "",
|
9 |
"add_cross_attention": true,
|
|
|
54 |
"output_attentions": false,
|
55 |
"output_hidden_states": false,
|
56 |
"output_scores": false,
|
57 |
+
"pad_token_id": 13,
|
58 |
"position_embedding_type": "absolute",
|
59 |
"prefix": null,
|
60 |
"problem_type": null,
|
|
|
79 |
"typical_p": 1.0,
|
80 |
"use_bfloat16": false,
|
81 |
"use_cache": true,
|
82 |
+
"vocab_size": 14
|
83 |
},
|
84 |
"decoder_start_token_id": 11,
|
85 |
"encoder": {
|
|
|
132 |
"output_attentions": false,
|
133 |
"output_hidden_states": false,
|
134 |
"output_scores": false,
|
135 |
+
"pad_token_id": 13,
|
136 |
"position_embedding_type": "absolute",
|
137 |
"prefix": null,
|
138 |
"problem_type": null,
|
|
|
157 |
"typical_p": 1.0,
|
158 |
"use_bfloat16": false,
|
159 |
"use_cache": true,
|
160 |
+
"vocab_size": 14
|
161 |
},
|
162 |
+
"eos_token_id": 12,
|
163 |
"is_encoder_decoder": true,
|
164 |
"model_type": "encoder-decoder",
|
165 |
+
"pad_token_id": 13,
|
166 |
"torch_dtype": "float32",
|
167 |
"transformers_version": null
|
168 |
}
|
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:e02c5c9098359dd6f2cb71eb401ca5889935b907919d2fbde3564fa71e894817
|
3 |
+
size 23603883
|
special_tokens_map.json
CHANGED
@@ -1 +1,5 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<pad>"
|
5 |
+
}
|
tokenizer.json
CHANGED
@@ -3,9 +3,81 @@
|
|
3 |
"truncation": null,
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
{
|
7 |
"id": 8,
|
8 |
-
"content": "
|
9 |
"single_word": false,
|
10 |
"lstrip": false,
|
11 |
"rstrip": false,
|
@@ -14,7 +86,7 @@
|
|
14 |
},
|
15 |
{
|
16 |
"id": 9,
|
17 |
-
"content": "
|
18 |
"single_word": false,
|
19 |
"lstrip": false,
|
20 |
"rstrip": false,
|
@@ -23,7 +95,7 @@
|
|
23 |
},
|
24 |
{
|
25 |
"id": 10,
|
26 |
-
"content": "
|
27 |
"single_word": false,
|
28 |
"lstrip": false,
|
29 |
"rstrip": false,
|
@@ -41,6 +113,15 @@
|
|
41 |
},
|
42 |
{
|
43 |
"id": 12,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
44 |
"content": "<pad>",
|
45 |
"single_word": false,
|
46 |
"lstrip": false,
|
@@ -61,6 +142,12 @@
|
|
61 |
"post_processor": {
|
62 |
"type": "TemplateProcessing",
|
63 |
"single": [
|
|
|
|
|
|
|
|
|
|
|
|
|
64 |
{
|
65 |
"Sequence": {
|
66 |
"id": "A",
|
@@ -69,7 +156,7 @@
|
|
69 |
},
|
70 |
{
|
71 |
"SpecialToken": {
|
72 |
-
"id": "
|
73 |
"type_id": 0
|
74 |
}
|
75 |
}
|
@@ -89,6 +176,15 @@
|
|
89 |
}
|
90 |
],
|
91 |
"special_tokens": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
92 |
"<s>": {
|
93 |
"id": "<s>",
|
94 |
"ids": [
|
@@ -103,16 +199,7 @@
|
|
103 |
"decoder": null,
|
104 |
"model": {
|
105 |
"type": "WordLevel",
|
106 |
-
"vocab": {
|
107 |
-
"-4": 0,
|
108 |
-
"-3": 1,
|
109 |
-
"-2": 2,
|
110 |
-
"-1": 3,
|
111 |
-
"1": 4,
|
112 |
-
"2": 5,
|
113 |
-
"3": 6,
|
114 |
-
"4": 7
|
115 |
-
},
|
116 |
"unk_token": "<unk>"
|
117 |
}
|
118 |
}
|
|
|
3 |
"truncation": null,
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
+
{
|
7 |
+
"id": 0,
|
8 |
+
"content": "1",
|
9 |
+
"single_word": false,
|
10 |
+
"lstrip": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"special": false
|
14 |
+
},
|
15 |
+
{
|
16 |
+
"id": 1,
|
17 |
+
"content": "-1",
|
18 |
+
"single_word": false,
|
19 |
+
"lstrip": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"normalized": true,
|
22 |
+
"special": false
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"id": 2,
|
26 |
+
"content": "2",
|
27 |
+
"single_word": false,
|
28 |
+
"lstrip": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"special": false
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"id": 3,
|
35 |
+
"content": "-2",
|
36 |
+
"single_word": false,
|
37 |
+
"lstrip": false,
|
38 |
+
"rstrip": false,
|
39 |
+
"normalized": true,
|
40 |
+
"special": false
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"id": 4,
|
44 |
+
"content": "3",
|
45 |
+
"single_word": false,
|
46 |
+
"lstrip": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"normalized": true,
|
49 |
+
"special": false
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"id": 5,
|
53 |
+
"content": "-3",
|
54 |
+
"single_word": false,
|
55 |
+
"lstrip": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"normalized": true,
|
58 |
+
"special": false
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"id": 6,
|
62 |
+
"content": "4",
|
63 |
+
"single_word": false,
|
64 |
+
"lstrip": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"normalized": true,
|
67 |
+
"special": false
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"id": 7,
|
71 |
+
"content": "-4",
|
72 |
+
"single_word": false,
|
73 |
+
"lstrip": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"normalized": true,
|
76 |
+
"special": false
|
77 |
+
},
|
78 |
{
|
79 |
"id": 8,
|
80 |
+
"content": "[",
|
81 |
"single_word": false,
|
82 |
"lstrip": false,
|
83 |
"rstrip": false,
|
|
|
86 |
},
|
87 |
{
|
88 |
"id": 9,
|
89 |
+
"content": "]",
|
90 |
"single_word": false,
|
91 |
"lstrip": false,
|
92 |
"rstrip": false,
|
|
|
95 |
},
|
96 |
{
|
97 |
"id": 10,
|
98 |
+
"content": ",",
|
99 |
"single_word": false,
|
100 |
"lstrip": false,
|
101 |
"rstrip": false,
|
|
|
113 |
},
|
114 |
{
|
115 |
"id": 12,
|
116 |
+
"content": "</s>",
|
117 |
+
"single_word": false,
|
118 |
+
"lstrip": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"id": 13,
|
125 |
"content": "<pad>",
|
126 |
"single_word": false,
|
127 |
"lstrip": false,
|
|
|
142 |
"post_processor": {
|
143 |
"type": "TemplateProcessing",
|
144 |
"single": [
|
145 |
+
{
|
146 |
+
"SpecialToken": {
|
147 |
+
"id": "<s>",
|
148 |
+
"type_id": 0
|
149 |
+
}
|
150 |
+
},
|
151 |
{
|
152 |
"Sequence": {
|
153 |
"id": "A",
|
|
|
156 |
},
|
157 |
{
|
158 |
"SpecialToken": {
|
159 |
+
"id": "</s>",
|
160 |
"type_id": 0
|
161 |
}
|
162 |
}
|
|
|
176 |
}
|
177 |
],
|
178 |
"special_tokens": {
|
179 |
+
"</s>": {
|
180 |
+
"id": "</s>",
|
181 |
+
"ids": [
|
182 |
+
12
|
183 |
+
],
|
184 |
+
"tokens": [
|
185 |
+
"</s>"
|
186 |
+
]
|
187 |
+
},
|
188 |
"<s>": {
|
189 |
"id": "<s>",
|
190 |
"ids": [
|
|
|
199 |
"decoder": null,
|
200 |
"model": {
|
201 |
"type": "WordLevel",
|
202 |
+
"vocab": {},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
203 |
"unk_token": "<unk>"
|
204 |
}
|
205 |
}
|
tokenizer_config.json
CHANGED
@@ -1,3 +1,8 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
2 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
3 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"name_or_path": "/home/kibrq/draft/tokenizer/word-level-tokenizer-4",
|
5 |
+
"pad_token": "<pad>",
|
6 |
+
"special_tokens_map_file": "/home/kibrq/draft/tokenizer/word-level-tokenizer-4/special_tokens_map.json",
|
7 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
8 |
}
|