Upload tokenizer
Browse files- special_tokens_map.json +6 -0
- tokenizer.json +39 -21
- tokenizer_config.json +9 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
tokenizer.json
CHANGED
@@ -2,27 +2,6 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": null,
|
4 |
"padding": null,
|
5 |
-
"normalizer": {
|
6 |
-
"type": "NFC"
|
7 |
-
},
|
8 |
-
"pre_tokenizer": {
|
9 |
-
"type": "ByteLevel",
|
10 |
-
"add_prefix_space": false,
|
11 |
-
"trim_offsets": true,
|
12 |
-
"use_regex": true
|
13 |
-
},
|
14 |
-
"post_processor": {
|
15 |
-
"type": "ByteLevel",
|
16 |
-
"add_prefix_space": false,
|
17 |
-
"trim_offsets": true,
|
18 |
-
"use_regex": true
|
19 |
-
},
|
20 |
-
"decoder": {
|
21 |
-
"type": "ByteLevel",
|
22 |
-
"add_prefix_space": false,
|
23 |
-
"trim_offsets": true,
|
24 |
-
"use_regex": true
|
25 |
-
},
|
26 |
"added_tokens": [
|
27 |
{
|
28 |
"id": 0,
|
@@ -9239,8 +9218,47 @@
|
|
9239 |
"rstrip": false,
|
9240 |
"normalized": true,
|
9241 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9242 |
}
|
9243 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9244 |
"model": {
|
9245 |
"type": "BPE",
|
9246 |
"dropout": null,
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": null,
|
4 |
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
|
|
9218 |
"rstrip": false,
|
9219 |
"normalized": true,
|
9220 |
"special": false
|
9221 |
+
},
|
9222 |
+
{
|
9223 |
+
"id": 1024,
|
9224 |
+
"content": "<|endoftext|>",
|
9225 |
+
"single_word": false,
|
9226 |
+
"lstrip": false,
|
9227 |
+
"rstrip": false,
|
9228 |
+
"normalized": false,
|
9229 |
+
"special": true
|
9230 |
+
},
|
9231 |
+
{
|
9232 |
+
"id": 1025,
|
9233 |
+
"content": "[PAD]",
|
9234 |
+
"single_word": false,
|
9235 |
+
"lstrip": false,
|
9236 |
+
"rstrip": false,
|
9237 |
+
"normalized": false,
|
9238 |
+
"special": true
|
9239 |
}
|
9240 |
],
|
9241 |
+
"normalizer": {
|
9242 |
+
"type": "NFC"
|
9243 |
+
},
|
9244 |
+
"pre_tokenizer": {
|
9245 |
+
"type": "ByteLevel",
|
9246 |
+
"add_prefix_space": false,
|
9247 |
+
"trim_offsets": true,
|
9248 |
+
"use_regex": true
|
9249 |
+
},
|
9250 |
+
"post_processor": {
|
9251 |
+
"type": "ByteLevel",
|
9252 |
+
"add_prefix_space": false,
|
9253 |
+
"trim_offsets": true,
|
9254 |
+
"use_regex": true
|
9255 |
+
},
|
9256 |
+
"decoder": {
|
9257 |
+
"type": "ByteLevel",
|
9258 |
+
"add_prefix_space": false,
|
9259 |
+
"trim_offsets": true,
|
9260 |
+
"use_regex": true
|
9261 |
+
},
|
9262 |
"model": {
|
9263 |
"type": "BPE",
|
9264 |
"dropout": null,
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "<|endoftext|>",
|
6 |
+
"model_max_length": 1000000000000000019884624838656,
|
7 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|