Upload tokenizer
Browse files- special_tokens_map.json +7 -1
- tokenizer_config.json +4 -34
special_tokens_map.json
CHANGED
@@ -13,7 +13,13 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
"unk_token": {
|
18 |
"content": "<|endoftext|>",
|
19 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
"unk_token": {
|
24 |
"content": "<|endoftext|>",
|
25 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -11,42 +11,12 @@
|
|
11 |
"special": true
|
12 |
}
|
13 |
},
|
14 |
-
"bos_token":
|
15 |
-
"__type": "AddedToken",
|
16 |
-
"content": "<|endoftext|>",
|
17 |
-
"lstrip": false,
|
18 |
-
"normalized": true,
|
19 |
-
"rstrip": false,
|
20 |
-
"single_word": false
|
21 |
-
},
|
22 |
"clean_up_tokenization_spaces": true,
|
23 |
-
"eos_token":
|
24 |
-
"__type": "AddedToken",
|
25 |
-
"content": "<|endoftext|>",
|
26 |
-
"lstrip": false,
|
27 |
-
"normalized": true,
|
28 |
-
"rstrip": false,
|
29 |
-
"single_word": false
|
30 |
-
},
|
31 |
"errors": "replace",
|
32 |
"model_max_length": 1024,
|
33 |
-
"
|
34 |
-
"pad_token": {
|
35 |
-
"__type": "AddedToken",
|
36 |
-
"content": "<|endoftext|>",
|
37 |
-
"lstrip": false,
|
38 |
-
"normalized": true,
|
39 |
-
"rstrip": false,
|
40 |
-
"single_word": false
|
41 |
-
},
|
42 |
-
"special_tokens_map_file": "/home/jsinha_umass_edu/Controlled-Text-Generation/output/20240312/gpt2_positive_expert/gpt2_164511/special_tokens_map.json",
|
43 |
"tokenizer_class": "GPT2Tokenizer",
|
44 |
-
"unk_token":
|
45 |
-
"__type": "AddedToken",
|
46 |
-
"content": "<|endoftext|>",
|
47 |
-
"lstrip": false,
|
48 |
-
"normalized": true,
|
49 |
-
"rstrip": false,
|
50 |
-
"single_word": false
|
51 |
-
}
|
52 |
}
|
|
|
11 |
"special": true
|
12 |
}
|
13 |
},
|
14 |
+
"bos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
"clean_up_tokenization_spaces": true,
|
16 |
+
"eos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
"errors": "replace",
|
18 |
"model_max_length": 1024,
|
19 |
+
"pad_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
"tokenizer_class": "GPT2Tokenizer",
|
21 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
}
|