Upload tokenizer
Browse files- special_tokens_map.json +3 -3
- tokenizer.model +3 -0
- tokenizer_config.json +7 -6
special_tokens_map.json
CHANGED
|
@@ -2,21 +2,21 @@
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "<s>",
|
| 4 |
"lstrip": false,
|
| 5 |
-
"normalized":
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
"content": "</s>",
|
| 11 |
"lstrip": false,
|
| 12 |
-
"normalized":
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"unk_token": {
|
| 17 |
"content": "<unk>",
|
| 18 |
"lstrip": false,
|
| 19 |
-
"normalized":
|
| 20 |
"rstrip": false,
|
| 21 |
"single_word": false
|
| 22 |
}
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "<s>",
|
| 4 |
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
"content": "</s>",
|
| 11 |
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"unk_token": {
|
| 17 |
"content": "<unk>",
|
| 18 |
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
"rstrip": false,
|
| 21 |
"single_word": false
|
| 22 |
}
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
CHANGED
|
@@ -1,11 +1,12 @@
|
|
| 1 |
{
|
| 2 |
"add_bos_token": true,
|
| 3 |
"add_eos_token": false,
|
|
|
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
| 7 |
"lstrip": false,
|
| 8 |
-
"normalized":
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false,
|
| 11 |
"special": true
|
|
@@ -13,7 +14,7 @@
|
|
| 13 |
"1": {
|
| 14 |
"content": "<s>",
|
| 15 |
"lstrip": false,
|
| 16 |
-
"normalized":
|
| 17 |
"rstrip": false,
|
| 18 |
"single_word": false,
|
| 19 |
"special": true
|
|
@@ -21,7 +22,7 @@
|
|
| 21 |
"2": {
|
| 22 |
"content": "</s>",
|
| 23 |
"lstrip": false,
|
| 24 |
-
"normalized":
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
|
@@ -30,11 +31,11 @@
|
|
| 30 |
"bos_token": "<s>",
|
| 31 |
"clean_up_tokenization_spaces": false,
|
| 32 |
"eos_token": "</s>",
|
| 33 |
-
"legacy":
|
| 34 |
-
"model_max_length":
|
| 35 |
"pad_token": null,
|
| 36 |
-
"padding_side": "right",
|
| 37 |
"sp_model_kwargs": {},
|
|
|
|
| 38 |
"tokenizer_class": "LlamaTokenizer",
|
| 39 |
"unk_token": "<unk>",
|
| 40 |
"use_default_system_prompt": false
|
|
|
|
| 1 |
{
|
| 2 |
"add_bos_token": true,
|
| 3 |
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
"0": {
|
| 7 |
"content": "<unk>",
|
| 8 |
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
"rstrip": false,
|
| 11 |
"single_word": false,
|
| 12 |
"special": true
|
|
|
|
| 14 |
"1": {
|
| 15 |
"content": "<s>",
|
| 16 |
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
"rstrip": false,
|
| 19 |
"single_word": false,
|
| 20 |
"special": true
|
|
|
|
| 22 |
"2": {
|
| 23 |
"content": "</s>",
|
| 24 |
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
"rstrip": false,
|
| 27 |
"single_word": false,
|
| 28 |
"special": true
|
|
|
|
| 31 |
"bos_token": "<s>",
|
| 32 |
"clean_up_tokenization_spaces": false,
|
| 33 |
"eos_token": "</s>",
|
| 34 |
+
"legacy": true,
|
| 35 |
+
"model_max_length": 2048,
|
| 36 |
"pad_token": null,
|
|
|
|
| 37 |
"sp_model_kwargs": {},
|
| 38 |
+
"spaces_between_special_tokens": false,
|
| 39 |
"tokenizer_class": "LlamaTokenizer",
|
| 40 |
"unk_token": "<unk>",
|
| 41 |
"use_default_system_prompt": false
|