Upload 3 files
Browse files- special_tokens_map.json +0 -7
- tokenizer.json +0 -0
- tokenizer_config.json +5 -14
special_tokens_map.json
CHANGED
|
@@ -35,12 +35,5 @@
|
|
| 35 |
"normalized": false,
|
| 36 |
"rstrip": false,
|
| 37 |
"single_word": false
|
| 38 |
-
},
|
| 39 |
-
"unk_token": {
|
| 40 |
-
"content": "<|unk|>",
|
| 41 |
-
"lstrip": false,
|
| 42 |
-
"normalized": false,
|
| 43 |
-
"rstrip": false,
|
| 44 |
-
"single_word": false
|
| 45 |
}
|
| 46 |
}
|
|
|
|
| 35 |
"normalized": false,
|
| 36 |
"rstrip": false,
|
| 37 |
"single_word": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
}
|
| 39 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,14 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
-
"content": "<|unk|>",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false,
|
| 9 |
-
"special": true
|
| 10 |
-
},
|
| 11 |
-
"1": {
|
| 12 |
"content": "<|pad|>",
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": false,
|
|
@@ -16,7 +8,7 @@
|
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
-
"
|
| 20 |
"content": "<|bos|>",
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
|
@@ -24,7 +16,7 @@
|
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
-
"
|
| 28 |
"content": "<|eos|>",
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
|
@@ -32,7 +24,7 @@
|
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
-
"
|
| 36 |
"content": "<|im_start|>",
|
| 37 |
"lstrip": false,
|
| 38 |
"normalized": false,
|
|
@@ -40,7 +32,7 @@
|
|
| 40 |
"single_word": false,
|
| 41 |
"special": true
|
| 42 |
},
|
| 43 |
-
"
|
| 44 |
"content": "<|im_end|>",
|
| 45 |
"lstrip": false,
|
| 46 |
"normalized": false,
|
|
@@ -58,6 +50,5 @@
|
|
| 58 |
"eos_token": "<|eos|>",
|
| 59 |
"model_max_length": 1000000000000000019884624838656,
|
| 60 |
"pad_token": "<|pad|>",
|
| 61 |
-
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 62 |
-
"unk_token": "<|unk|>"
|
| 63 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"content": "<|pad|>",
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": false,
|
|
|
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
+
"1": {
|
| 12 |
"content": "<|bos|>",
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": false,
|
|
|
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
+
"2": {
|
| 20 |
"content": "<|eos|>",
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
|
|
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
+
"3": {
|
| 28 |
"content": "<|im_start|>",
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
|
|
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
+
"4": {
|
| 36 |
"content": "<|im_end|>",
|
| 37 |
"lstrip": false,
|
| 38 |
"normalized": false,
|
|
|
|
| 50 |
"eos_token": "<|eos|>",
|
| 51 |
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
"pad_token": "<|pad|>",
|
| 53 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
|
| 54 |
}
|