filipemiguelmartins
commited on
Commit
•
1f24bf1
1
Parent(s):
e2ea3a9
Upload tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer.json +2 -23
- tokenizer_config.json +1 -10
special_tokens_map.json
CHANGED
@@ -13,5 +13,5 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token": "
|
17 |
}
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "<|eot_id|>"
|
17 |
}
|
tokenizer.json
CHANGED
@@ -1,19 +1,7 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
5 |
-
"max_length": 128,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
-
"padding": {
|
10 |
-
"strategy": "BatchLongest",
|
11 |
-
"direction": "Right",
|
12 |
-
"pad_to_multiple_of": 8,
|
13 |
-
"pad_id": 128256,
|
14 |
-
"pad_type_id": 0,
|
15 |
-
"pad_token": "[PAD]"
|
16 |
-
},
|
17 |
"added_tokens": [
|
18 |
{
|
19 |
"id": 128000,
|
@@ -2318,15 +2306,6 @@
|
|
2318 |
"rstrip": false,
|
2319 |
"normalized": false,
|
2320 |
"special": true
|
2321 |
-
},
|
2322 |
-
{
|
2323 |
-
"id": 128256,
|
2324 |
-
"content": "[PAD]",
|
2325 |
-
"single_word": false,
|
2326 |
-
"lstrip": false,
|
2327 |
-
"rstrip": false,
|
2328 |
-
"normalized": false,
|
2329 |
-
"special": true
|
2330 |
}
|
2331 |
],
|
2332 |
"normalizer": null,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 128000,
|
|
|
2306 |
"rstrip": false,
|
2307 |
"normalized": false,
|
2308 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2309 |
}
|
2310 |
],
|
2311 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
{
|
2 |
-
"add_eos_token": true,
|
3 |
"added_tokens_decoder": {
|
4 |
"128000": {
|
5 |
"content": "<|begin_of_text|>",
|
@@ -2048,14 +2047,6 @@
|
|
2048 |
"rstrip": false,
|
2049 |
"single_word": false,
|
2050 |
"special": true
|
2051 |
-
},
|
2052 |
-
"128256": {
|
2053 |
-
"content": "[PAD]",
|
2054 |
-
"lstrip": false,
|
2055 |
-
"normalized": false,
|
2056 |
-
"rstrip": false,
|
2057 |
-
"single_word": false,
|
2058 |
-
"special": true
|
2059 |
}
|
2060 |
},
|
2061 |
"bos_token": "<|begin_of_text|>",
|
@@ -2067,6 +2058,6 @@
|
|
2067 |
"attention_mask"
|
2068 |
],
|
2069 |
"model_max_length": 1000000000000000019884624838656,
|
2070 |
-
"pad_token": "
|
2071 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2072 |
}
|
|
|
1 |
{
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"128000": {
|
4 |
"content": "<|begin_of_text|>",
|
|
|
2047 |
"rstrip": false,
|
2048 |
"single_word": false,
|
2049 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
|
|
2058 |
"attention_mask"
|
2059 |
],
|
2060 |
"model_max_length": 1000000000000000019884624838656,
|
2061 |
+
"pad_token": "<|eot_id|>",
|
2062 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
}
|