update tokenizers
Browse files- tokenizer.json +2 -2
- tokenizer_config.json +5 -19
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 sha256:358f1c052643d5f9f57704c5980b35fe94e94ccd8f007300a97d92360c4e3673
|
| 3 |
+
size 7319011
|
tokenizer_config.json
CHANGED
|
@@ -1,29 +1,15 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"bos_token":
|
| 5 |
-
"__type": "AddedToken",
|
| 6 |
-
"content": "|ENDOFTEXT|",
|
| 7 |
-
"lstrip": false,
|
| 8 |
-
"normalized": true,
|
| 9 |
-
"rstrip": false,
|
| 10 |
-
"single_word": false
|
| 11 |
-
},
|
| 12 |
"clean_up_tokenization_spaces": false,
|
| 13 |
"eos_token": null,
|
| 14 |
-
"
|
| 15 |
"model_max_length": 512,
|
| 16 |
"pad_token": null,
|
| 17 |
"sp_model_kwargs": {},
|
| 18 |
"spaces_between_special_tokens": false,
|
| 19 |
"tokenizer_class": "LlamaTokenizer",
|
| 20 |
-
"unk_token":
|
| 21 |
-
"__type": "AddedToken",
|
| 22 |
-
"content": "<unk>",
|
| 23 |
-
"lstrip": false,
|
| 24 |
-
"normalized": true,
|
| 25 |
-
"rstrip": false,
|
| 26 |
-
"single_word": false
|
| 27 |
-
},
|
| 28 |
"use_default_system_prompt": true
|
| 29 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_prefix_space": null,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "|ENDOFTEXT|",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"clean_up_tokenization_spaces": false,
|
| 6 |
"eos_token": null,
|
| 7 |
+
"is_local": false,
|
| 8 |
"model_max_length": 512,
|
| 9 |
"pad_token": null,
|
| 10 |
"sp_model_kwargs": {},
|
| 11 |
"spaces_between_special_tokens": false,
|
| 12 |
"tokenizer_class": "LlamaTokenizer",
|
| 13 |
+
"unk_token": "<unk>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
"use_default_system_prompt": true
|
| 15 |
}
|