Commit
·
8928510
1
Parent(s):
69a2579
Upload tokenizer
Browse files- added_tokens.json +0 -2
- merges.txt +0 -0
- special_tokens_map.json +3 -37
- tokenizer_config.json +0 -22
- vocab.json +0 -0
added_tokens.json
CHANGED
|
@@ -1,5 +1,3 @@
|
|
| 1 |
{
|
| 2 |
-
"<AI>": 50259,
|
| 3 |
-
"<USER>": 50258,
|
| 4 |
"[PAD]": 50257
|
| 5 |
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"[PAD]": 50257
|
| 3 |
}
|
merges.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
CHANGED
|
@@ -1,34 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
|
| 4 |
-
"content": "<USER>",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false
|
| 9 |
-
},
|
| 10 |
-
{
|
| 11 |
-
"content": "<AI>",
|
| 12 |
-
"lstrip": false,
|
| 13 |
-
"normalized": false,
|
| 14 |
-
"rstrip": false,
|
| 15 |
-
"single_word": false
|
| 16 |
-
}
|
| 17 |
-
],
|
| 18 |
-
"bos_token": {
|
| 19 |
-
"content": "<|endoftext|>",
|
| 20 |
-
"lstrip": false,
|
| 21 |
-
"normalized": true,
|
| 22 |
-
"rstrip": false,
|
| 23 |
-
"single_word": false
|
| 24 |
-
},
|
| 25 |
-
"eos_token": {
|
| 26 |
-
"content": "<|endoftext|>",
|
| 27 |
-
"lstrip": false,
|
| 28 |
-
"normalized": true,
|
| 29 |
-
"rstrip": false,
|
| 30 |
-
"single_word": false
|
| 31 |
-
},
|
| 32 |
"pad_token": {
|
| 33 |
"content": "[PAD]",
|
| 34 |
"lstrip": false,
|
|
@@ -36,11 +8,5 @@
|
|
| 36 |
"rstrip": false,
|
| 37 |
"single_word": false
|
| 38 |
},
|
| 39 |
-
"unk_token":
|
| 40 |
-
"content": "<|endoftext|>",
|
| 41 |
-
"lstrip": false,
|
| 42 |
-
"normalized": true,
|
| 43 |
-
"rstrip": false,
|
| 44 |
-
"single_word": false
|
| 45 |
-
}
|
| 46 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"pad_token": {
|
| 5 |
"content": "[PAD]",
|
| 6 |
"lstrip": false,
|
|
|
|
| 8 |
"rstrip": false,
|
| 9 |
"single_word": false
|
| 10 |
},
|
| 11 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
}
|
tokenizer_config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token": false,
|
| 3 |
"add_prefix_space": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"50256": {
|
|
@@ -17,32 +16,11 @@
|
|
| 17 |
"rstrip": false,
|
| 18 |
"single_word": false,
|
| 19 |
"special": true
|
| 20 |
-
},
|
| 21 |
-
"50258": {
|
| 22 |
-
"content": "<USER>",
|
| 23 |
-
"lstrip": false,
|
| 24 |
-
"normalized": false,
|
| 25 |
-
"rstrip": false,
|
| 26 |
-
"single_word": false,
|
| 27 |
-
"special": true
|
| 28 |
-
},
|
| 29 |
-
"50259": {
|
| 30 |
-
"content": "<AI>",
|
| 31 |
-
"lstrip": false,
|
| 32 |
-
"normalized": false,
|
| 33 |
-
"rstrip": false,
|
| 34 |
-
"single_word": false,
|
| 35 |
-
"special": true
|
| 36 |
}
|
| 37 |
},
|
| 38 |
-
"additional_special_tokens": [
|
| 39 |
-
"<USER>",
|
| 40 |
-
"<AI>"
|
| 41 |
-
],
|
| 42 |
"bos_token": "<|endoftext|>",
|
| 43 |
"clean_up_tokenization_spaces": false,
|
| 44 |
"eos_token": "<|endoftext|>",
|
| 45 |
-
"errors": "replace",
|
| 46 |
"extra_special_tokens": {},
|
| 47 |
"model_max_length": 1024,
|
| 48 |
"pad_token": "[PAD]",
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"50256": {
|
|
|
|
| 16 |
"rstrip": false,
|
| 17 |
"single_word": false,
|
| 18 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
}
|
| 20 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
"bos_token": "<|endoftext|>",
|
| 22 |
"clean_up_tokenization_spaces": false,
|
| 23 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 24 |
"extra_special_tokens": {},
|
| 25 |
"model_max_length": 1024,
|
| 26 |
"pad_token": "[PAD]",
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|