Upload 3 files
Browse files- special_tokens_map.json +0 -23
- tokenizer.json +0 -0
- tokenizer_config.json +1 -22
special_tokens_map.json
CHANGED
|
@@ -1,20 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
{
|
| 4 |
-
"content": "<think>",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false
|
| 9 |
-
},
|
| 10 |
-
{
|
| 11 |
-
"content": "</think>",
|
| 12 |
-
"lstrip": false,
|
| 13 |
-
"normalized": false,
|
| 14 |
-
"rstrip": false,
|
| 15 |
-
"single_word": false
|
| 16 |
-
}
|
| 17 |
-
],
|
| 18 |
"bos_token": {
|
| 19 |
"content": "<|begin_of_text|>",
|
| 20 |
"lstrip": false,
|
|
@@ -28,12 +12,5 @@
|
|
| 28 |
"normalized": false,
|
| 29 |
"rstrip": false,
|
| 30 |
"single_word": false
|
| 31 |
-
},
|
| 32 |
-
"pad_token": {
|
| 33 |
-
"content": "<|reserved_special_token_247|>",
|
| 34 |
-
"lstrip": false,
|
| 35 |
-
"normalized": false,
|
| 36 |
-
"rstrip": false,
|
| 37 |
-
"single_word": false
|
| 38 |
}
|
| 39 |
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "<|begin_of_text|>",
|
| 4 |
"lstrip": false,
|
|
|
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
}
|
| 16 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -2047,28 +2047,8 @@
|
|
| 2047 |
"rstrip": false,
|
| 2048 |
"single_word": false,
|
| 2049 |
"special": true
|
| 2050 |
-
},
|
| 2051 |
-
"128256": {
|
| 2052 |
-
"content": "<think>",
|
| 2053 |
-
"lstrip": false,
|
| 2054 |
-
"normalized": false,
|
| 2055 |
-
"rstrip": false,
|
| 2056 |
-
"single_word": false,
|
| 2057 |
-
"special": true
|
| 2058 |
-
},
|
| 2059 |
-
"128257": {
|
| 2060 |
-
"content": "</think>",
|
| 2061 |
-
"lstrip": false,
|
| 2062 |
-
"normalized": false,
|
| 2063 |
-
"rstrip": false,
|
| 2064 |
-
"single_word": false,
|
| 2065 |
-
"special": true
|
| 2066 |
}
|
| 2067 |
},
|
| 2068 |
-
"additional_special_tokens": [
|
| 2069 |
-
"<think>",
|
| 2070 |
-
"</think>"
|
| 2071 |
-
],
|
| 2072 |
"bos_token": "<|begin_of_text|>",
|
| 2073 |
"clean_up_tokenization_spaces": true,
|
| 2074 |
"eos_token": "<|end_of_text|>",
|
|
@@ -2078,6 +2058,5 @@
|
|
| 2078 |
"attention_mask"
|
| 2079 |
],
|
| 2080 |
"model_max_length": 131072,
|
| 2081 |
-
"
|
| 2082 |
-
"tokenizer_class": "PreTrainedTokenizer"
|
| 2083 |
}
|
|
|
|
| 2047 |
"rstrip": false,
|
| 2048 |
"single_word": false,
|
| 2049 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2050 |
}
|
| 2051 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2052 |
"bos_token": "<|begin_of_text|>",
|
| 2053 |
"clean_up_tokenization_spaces": true,
|
| 2054 |
"eos_token": "<|end_of_text|>",
|
|
|
|
| 2058 |
"attention_mask"
|
| 2059 |
],
|
| 2060 |
"model_max_length": 131072,
|
| 2061 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
|
| 2062 |
}
|