Update tokenizer
#11
by
RaymondLi
- opened
- special_tokens_map.json +9 -1
- tokenizer.json +47 -1
- tokenizer_config.json +1 -3
special_tokens_map.json
CHANGED
|
@@ -1 +1,9 @@
|
|
| 1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<fim-prefix>",
|
| 5 |
+
"<fim-middle>",
|
| 6 |
+
"<fim-suffix>",
|
| 7 |
+
"<fim-pad>"
|
| 8 |
+
]
|
| 9 |
+
}
|
tokenizer.json
CHANGED
|
@@ -2,7 +2,53 @@
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": null,
|
| 4 |
"padding": null,
|
| 5 |
-
"added_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"normalizer": null,
|
| 7 |
"pre_tokenizer": {
|
| 8 |
"type": "Sequence",
|
|
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": null,
|
| 4 |
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 49152,
|
| 8 |
+
"content": "<|endoftext|>",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 49153,
|
| 17 |
+
"content": "<fim-prefix>",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 49154,
|
| 26 |
+
"content": "<fim-middle>",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 49155,
|
| 35 |
+
"content": "<fim-suffix>",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 49156,
|
| 44 |
+
"content": "<fim-pad>",
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"special": true
|
| 50 |
+
}
|
| 51 |
+
],
|
| 52 |
"normalizer": null,
|
| 53 |
"pre_tokenizer": {
|
| 54 |
"type": "Sequence",
|
tokenizer_config.json
CHANGED
|
@@ -1,7 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"special_tokens_map_file": "/Users/leandro/.cache/huggingface/hub/models--bigcode--digit-bytelevel-bpe-jss-v1.1-49152/snapshots/fa09b77949689a484afafc5f89534e6b6ba2c151/special_tokens_map.json",
|
| 4 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 5 |
-
"vocab_size": 49152,
|
| 6 |
"model_max_length": 2048
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"errors": "replace",
|
|
|
|
| 3 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
|
|
|
| 4 |
"model_max_length": 2048
|
| 5 |
}
|