Upload tokenizer
Browse files- added_tokens.json +5 -2
- merges.txt +4 -0
- tokenizer.json +0 -0
- tokenizer_config.json +24 -16
- vocab.json +0 -0
added_tokens.json
CHANGED
|
@@ -4,6 +4,9 @@
|
|
| 4 |
"<pad>": 8003,
|
| 5 |
"<s>": 8000,
|
| 6 |
"<unk>": 8002,
|
| 7 |
-
"<|assistant|>":
|
| 8 |
-
"<|endoftext|>": 8005
|
|
|
|
|
|
|
|
|
|
| 9 |
}
|
|
|
|
| 4 |
"<pad>": 8003,
|
| 5 |
"<s>": 8000,
|
| 6 |
"<unk>": 8002,
|
| 7 |
+
"<|assistant|>": 8008,
|
| 8 |
+
"<|endoftext|>": 8005,
|
| 9 |
+
"<|end|>": 8007,
|
| 10 |
+
"<|system|>": 8009,
|
| 11 |
+
"<|user|>": 8006
|
| 12 |
}
|
merges.txt
CHANGED
|
@@ -7739,3 +7739,7 @@ bal anced
|
|
| 7739 |
Ġoverwhel med
|
| 7740 |
Ġlic ense
|
| 7741 |
Ġflood ing
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7739 |
Ġoverwhel med
|
| 7740 |
Ġlic ense
|
| 7741 |
Ġflood ing
|
| 7742 |
+
Ġcrow d
|
| 7743 |
+
Ġtow ns
|
| 7744 |
+
ĠEle phant
|
| 7745 |
+
Ġwond ers
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,22 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
-
"2": {
|
| 5 |
-
"content": "<|end|>",
|
| 6 |
-
"lstrip": false,
|
| 7 |
-
"normalized": false,
|
| 8 |
-
"rstrip": false,
|
| 9 |
-
"single_word": false,
|
| 10 |
-
"special": true
|
| 11 |
-
},
|
| 12 |
-
"3": {
|
| 13 |
-
"content": "<|user|>",
|
| 14 |
-
"lstrip": false,
|
| 15 |
-
"normalized": false,
|
| 16 |
-
"rstrip": false,
|
| 17 |
-
"single_word": false,
|
| 18 |
-
"special": true
|
| 19 |
-
},
|
| 20 |
"8000": {
|
| 21 |
"content": "<s>",
|
| 22 |
"lstrip": false,
|
|
@@ -66,12 +50,36 @@
|
|
| 66 |
"special": true
|
| 67 |
},
|
| 68 |
"8006": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
"content": "<|assistant|>",
|
| 70 |
"lstrip": false,
|
| 71 |
"normalized": true,
|
| 72 |
"rstrip": false,
|
| 73 |
"single_word": false,
|
| 74 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 75 |
}
|
| 76 |
},
|
| 77 |
"bos_token": "<|user|>",
|
|
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"8000": {
|
| 5 |
"content": "<s>",
|
| 6 |
"lstrip": false,
|
|
|
|
| 50 |
"special": true
|
| 51 |
},
|
| 52 |
"8006": {
|
| 53 |
+
"content": "<|user|>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"8007": {
|
| 61 |
+
"content": "<|end|>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"8008": {
|
| 69 |
"content": "<|assistant|>",
|
| 70 |
"lstrip": false,
|
| 71 |
"normalized": true,
|
| 72 |
"rstrip": false,
|
| 73 |
"single_word": false,
|
| 74 |
"special": false
|
| 75 |
+
},
|
| 76 |
+
"8009": {
|
| 77 |
+
"content": "<|system|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": true,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": false
|
| 83 |
}
|
| 84 |
},
|
| 85 |
"bos_token": "<|user|>",
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|