add tokenizer
Browse files- special_tokens_map.json +1 -23
- tokenizer_config.json +1 -32
special_tokens_map.json
CHANGED
@@ -1,23 +1 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": {
|
3 |
-
"content": "<|endoftext|>",
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": true,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "<|endoftext|>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": true,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"unk_token": {
|
17 |
-
"content": "<|endoftext|>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": true,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
}
|
23 |
-
}
|
|
|
1 |
+
{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer_config.json
CHANGED
@@ -1,32 +1 @@
|
|
1 |
-
{
|
2 |
-
"add_prefix_space": false,
|
3 |
-
"bos_token": {
|
4 |
-
"__type": "AddedToken",
|
5 |
-
"content": "<|endoftext|>",
|
6 |
-
"lstrip": false,
|
7 |
-
"normalized": true,
|
8 |
-
"rstrip": false,
|
9 |
-
"single_word": false
|
10 |
-
},
|
11 |
-
"eos_token": {
|
12 |
-
"__type": "AddedToken",
|
13 |
-
"content": "<|endoftext|>",
|
14 |
-
"lstrip": false,
|
15 |
-
"normalized": true,
|
16 |
-
"rstrip": false,
|
17 |
-
"single_word": false
|
18 |
-
},
|
19 |
-
"errors": "replace",
|
20 |
-
"model_max_length": 1024,
|
21 |
-
"name_or_path": "deepparag/Aeona-Beta",
|
22 |
-
"special_tokens_map_file": null,
|
23 |
-
"tokenizer_class": "GPT2Tokenizer",
|
24 |
-
"unk_token": {
|
25 |
-
"__type": "AddedToken",
|
26 |
-
"content": "<|endoftext|>",
|
27 |
-
"lstrip": false,
|
28 |
-
"normalized": true,
|
29 |
-
"rstrip": false,
|
30 |
-
"single_word": false
|
31 |
-
}
|
32 |
-
}
|
|
|
1 |
+
{"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, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "transfaeries/DialoGPT-medium-Discord-1.0", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|