Commit
•
6fbb95e
1
Parent(s):
060cac3
Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +1 -31
tokenizer_config.json
CHANGED
|
@@ -1,31 +1 @@
|
|
| 1 |
-
{
|
| 2 |
-
"errors": "replace",
|
| 3 |
-
"unk_token": {
|
| 4 |
-
"content": "<unk>",
|
| 5 |
-
"single_word": false,
|
| 6 |
-
"lstrip": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"normalized": true,
|
| 9 |
-
"__type": "AddedToken"
|
| 10 |
-
},
|
| 11 |
-
"bos_token": {
|
| 12 |
-
"content": "<s>",
|
| 13 |
-
"single_word": false,
|
| 14 |
-
"lstrip": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"normalized": true,
|
| 17 |
-
"__type": "AddedToken"
|
| 18 |
-
},
|
| 19 |
-
"eos_token": {
|
| 20 |
-
"content": "</s>",
|
| 21 |
-
"single_word": false,
|
| 22 |
-
"lstrip": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"normalized": true,
|
| 25 |
-
"__type": "AddedToken"
|
| 26 |
-
},
|
| 27 |
-
"add_prefix_space": false,
|
| 28 |
-
"special_tokens_map_file": null,
|
| 29 |
-
"tokenizer_file": null,
|
| 30 |
-
"name_or_path": "steeldream/letov"
|
| 31 |
-
}
|
|
|
|
| 1 |
+
{"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "sberbank-ai/rugpt3large_based_on_gpt2"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|