Upload 3 files
Browse files- special_tokens_map.json +2 -14
- tokenizer.json +2 -2
- tokenizer_config.json +1 -2
special_tokens_map.json
CHANGED
|
@@ -1,16 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
"lstrip": false,
|
| 5 |
-
"normalized": false,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"eos_token": {
|
| 10 |
-
"content": "<|end_of_text|>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": false,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
}
|
| 16 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<|begin_of_text|>",
|
| 3 |
+
"eos_token": "<|end_of_text|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
}
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e134af98b985517b4f068e3755ae90d4e9cd2d45d328325dc503f1c6b2d06cc7
|
| 3 |
+
size 9085698
|
tokenizer_config.json
CHANGED
|
@@ -2052,11 +2052,10 @@
|
|
| 2052 |
"bos_token": "<|begin_of_text|>",
|
| 2053 |
"clean_up_tokenization_spaces": true,
|
| 2054 |
"eos_token": "<|end_of_text|>",
|
| 2055 |
-
"extra_special_tokens": {},
|
| 2056 |
"model_input_names": [
|
| 2057 |
"input_ids",
|
| 2058 |
"attention_mask"
|
| 2059 |
],
|
| 2060 |
"model_max_length": 1000000000000000019884624838656,
|
| 2061 |
-
"tokenizer_class": "
|
| 2062 |
}
|
|
|
|
| 2052 |
"bos_token": "<|begin_of_text|>",
|
| 2053 |
"clean_up_tokenization_spaces": true,
|
| 2054 |
"eos_token": "<|end_of_text|>",
|
|
|
|
| 2055 |
"model_input_names": [
|
| 2056 |
"input_ids",
|
| 2057 |
"attention_mask"
|
| 2058 |
],
|
| 2059 |
"model_max_length": 1000000000000000019884624838656,
|
| 2060 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2061 |
}
|