Upload tokenizer
Browse files- special_tokens_map.json +5 -0
- tokenizer.model +3 -0
- tokenizer_config.json +37 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "<|endoftext|>",
|
3 |
+
"pad_token": "<|endoftext|>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05234874580b169d3ba5a59b004b655ddba73fc9ea5493451053374629d9295d
|
3 |
+
size 4569957
|
tokenizer_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
}
|
21 |
+
},
|
22 |
+
"auto_map": {
|
23 |
+
"AutoTokenizer": [
|
24 |
+
"aisingapore/sea-lion-3b--tokenization_SEA_BPE.SEABPETokenizer",
|
25 |
+
null
|
26 |
+
]
|
27 |
+
},
|
28 |
+
"bos_token": null,
|
29 |
+
"clean_up_tokenization_spaces": false,
|
30 |
+
"eos_token": "<|endoftext|>",
|
31 |
+
"legacy": true,
|
32 |
+
"model_max_length": 1000000000000000019884624838656,
|
33 |
+
"pad_token": null,
|
34 |
+
"sp_model_kwargs": {},
|
35 |
+
"tokenizer_class": "SEABPETokenizer",
|
36 |
+
"unk_token": "<unk>"
|
37 |
+
}
|