Commit
•
d9cbeb5
1
Parent(s):
399e229
Upload tokenizer
Browse files- added_tokens.json +3 -0
- special_tokens_map.json +7 -1
- tokenizer.json +1 -6
- tokenizer.model +3 -0
- tokenizer_config.json +3 -1
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<pad>": 32000
|
| 3 |
+
}
|
special_tokens_map.json
CHANGED
|
@@ -13,7 +13,13 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<unk>",
|
| 19 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
"unk_token": {
|
| 24 |
"content": "<unk>",
|
| 25 |
"lstrip": false,
|
tokenizer.json
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
"direction": "Right",
|
| 5 |
-
"max_length": 1024,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
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
|
@@ -1,4 +1,6 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
"content": "<unk>",
|
|
@@ -38,7 +40,7 @@
|
|
| 38 |
"eos_token": "</s>",
|
| 39 |
"legacy": false,
|
| 40 |
"model_max_length": 1000000000000000019884624838656,
|
| 41 |
-
"pad_token": "
|
| 42 |
"sp_model_kwargs": {},
|
| 43 |
"tokenizer_class": "LlamaTokenizer",
|
| 44 |
"unk_token": "<unk>",
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
|
|
|
| 40 |
"eos_token": "</s>",
|
| 41 |
"legacy": false,
|
| 42 |
"model_max_length": 1000000000000000019884624838656,
|
| 43 |
+
"pad_token": "<unk>",
|
| 44 |
"sp_model_kwargs": {},
|
| 45 |
"tokenizer_class": "LlamaTokenizer",
|
| 46 |
"unk_token": "<unk>",
|