Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer.json +2 -2
- tokenizer.model +3 -0
- tokenizer_config.json +26 -13
special_tokens_map.json
CHANGED
@@ -12,5 +12,12 @@
|
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
}
|
16 |
}
|
|
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
}
|
23 |
}
|
tokenizer.json
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:e27b8cc9cb1c7cdab5d45b0c8d027fd6e812afe70496917fc33bb336a79a346d
|
3 |
+
size 34810700
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dfd8b970f437002fc445214304969fe59e64d4f48500bd0b77ba55340f2d811
|
3 |
+
size 4545602
|
tokenizer_config.json
CHANGED
@@ -1,5 +1,24 @@
|
|
1 |
{
|
|
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"2": {
|
4 |
"content": "<s>",
|
5 |
"lstrip": false,
|
@@ -8015,23 +8034,17 @@
|
|
8015 |
"rstrip": false,
|
8016 |
"single_word": false,
|
8017 |
"special": false
|
8018 |
-
},
|
8019 |
-
"255999": {
|
8020 |
-
"content": "<pad>",
|
8021 |
-
"lstrip": false,
|
8022 |
-
"normalized": false,
|
8023 |
-
"rstrip": false,
|
8024 |
-
"single_word": false,
|
8025 |
-
"special": true
|
8026 |
}
|
8027 |
},
|
8028 |
"bos_token": "<s>",
|
8029 |
"clean_up_tokenization_spaces": false,
|
8030 |
"eos_token": "</s>",
|
8031 |
-
"
|
8032 |
-
"input_ids",
|
8033 |
-
"attention_mask"
|
8034 |
-
],
|
8035 |
"model_max_length": 1000000000000000019884624838656,
|
8036 |
-
"
|
|
|
|
|
|
|
|
|
|
|
8037 |
}
|
|
|
1 |
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<pad>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<unk>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
"2": {
|
23 |
"content": "<s>",
|
24 |
"lstrip": false,
|
|
|
8034 |
"rstrip": false,
|
8035 |
"single_word": false,
|
8036 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8037 |
}
|
8038 |
},
|
8039 |
"bos_token": "<s>",
|
8040 |
"clean_up_tokenization_spaces": false,
|
8041 |
"eos_token": "</s>",
|
8042 |
+
"legacy": false,
|
|
|
|
|
|
|
8043 |
"model_max_length": 1000000000000000019884624838656,
|
8044 |
+
"pad_token": null,
|
8045 |
+
"sp_model_kwargs": {},
|
8046 |
+
"spaces_between_special_tokens": false,
|
8047 |
+
"tokenizer_class": "LlamaTokenizer",
|
8048 |
+
"unk_token": "<unk>",
|
8049 |
+
"use_default_system_prompt": false
|
8050 |
}
|