Upload tokenizer
Browse files- tokenizer.json +2 -2
- tokenizer.model +3 -0
- tokenizer_config.json +0 -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 sha256:05e97791a5e007260de1db7e1692e53150e08cea481e2bf25435553380c147ee
|
| 3 |
+
size 17477929
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
| 3 |
+
size 4241003
|
tokenizer_config.json
CHANGED
|
@@ -60,15 +60,11 @@
|
|
| 60 |
"clean_up_tokenization_spaces": false,
|
| 61 |
"eos_token": "<eos>",
|
| 62 |
"legacy": null,
|
| 63 |
-
"max_length": 2048,
|
| 64 |
"model_max_length": 1000000000000000019884624838656,
|
| 65 |
"pad_token": "<pad>",
|
| 66 |
"sp_model_kwargs": {},
|
| 67 |
"spaces_between_special_tokens": false,
|
| 68 |
-
"stride": 0,
|
| 69 |
"tokenizer_class": "GemmaTokenizer",
|
| 70 |
-
"truncation_side": "right",
|
| 71 |
-
"truncation_strategy": "longest_first",
|
| 72 |
"unk_token": "<unk>",
|
| 73 |
"use_default_system_prompt": false
|
| 74 |
}
|
|
|
|
| 60 |
"clean_up_tokenization_spaces": false,
|
| 61 |
"eos_token": "<eos>",
|
| 62 |
"legacy": null,
|
|
|
|
| 63 |
"model_max_length": 1000000000000000019884624838656,
|
| 64 |
"pad_token": "<pad>",
|
| 65 |
"sp_model_kwargs": {},
|
| 66 |
"spaces_between_special_tokens": false,
|
|
|
|
| 67 |
"tokenizer_class": "GemmaTokenizer",
|
|
|
|
|
|
|
| 68 |
"unk_token": "<unk>",
|
| 69 |
"use_default_system_prompt": false
|
| 70 |
}
|