Update tokenizer_config.json
Browse files- tokenizer_config.json +14 -25
tokenizer_config.json
CHANGED
@@ -1,34 +1,23 @@
|
|
1 |
{
|
2 |
"add_bos_token": false,
|
3 |
"add_prefix_space": false,
|
4 |
-
"
|
5 |
-
"
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
"__type": "AddedToken",
|
14 |
-
"content": "<|endoftext|>",
|
15 |
-
"lstrip": false,
|
16 |
-
"normalized": true,
|
17 |
-
"rstrip": false,
|
18 |
-
"single_word": false
|
19 |
},
|
|
|
|
|
|
|
|
|
20 |
"errors": "replace",
|
21 |
"model_max_length": 1024,
|
22 |
-
"name_or_path": "microsoft/DialoGPT-medium",
|
23 |
"pad_token": null,
|
24 |
-
"special_tokens_map_file": null,
|
25 |
"tokenizer_class": "GPT2Tokenizer",
|
26 |
-
"unk_token":
|
27 |
-
"__type": "AddedToken",
|
28 |
-
"content": "<|endoftext|>",
|
29 |
-
"lstrip": false,
|
30 |
-
"normalized": true,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false
|
33 |
-
}
|
34 |
}
|
|
|
1 |
{
|
2 |
"add_bos_token": false,
|
3 |
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"50256": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
},
|
14 |
+
"bos_token": "<|endoftext|>",
|
15 |
+
"chat_template": "{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}",
|
16 |
+
"clean_up_tokenization_spaces": true,
|
17 |
+
"eos_token": "<|endoftext|>",
|
18 |
"errors": "replace",
|
19 |
"model_max_length": 1024,
|
|
|
20 |
"pad_token": null,
|
|
|
21 |
"tokenizer_class": "GPT2Tokenizer",
|
22 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
}
|