patrickvonplaten
commited on
Commit
•
c009356
1
Parent(s):
642ae4b
up
Browse files- added_tokens.json +5 -0
- config.json +3 -2
- special_tokens_map.json +12 -0
- tokenizer_config.json +33 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<BOS>": 50258,
|
3 |
+
"<EOS>": 50259,
|
4 |
+
"<PAD>": 50257
|
5 |
+
}
|
config.json
CHANGED
@@ -5,9 +5,10 @@
|
|
5 |
"GPT2OptimusForLatentConnector"
|
6 |
],
|
7 |
"attn_pdrop": 0.1,
|
8 |
-
"bos_token_id":
|
9 |
"embd_pdrop": 0.1,
|
10 |
-
"eos_token_id":
|
|
|
11 |
"id2label": {
|
12 |
"0": "LABEL_0"
|
13 |
},
|
|
|
5 |
"GPT2OptimusForLatentConnector"
|
6 |
],
|
7 |
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50258,
|
9 |
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50259,
|
11 |
+
"pad_token_id": 50257,
|
12 |
"id2label": {
|
13 |
"0": "LABEL_0"
|
14 |
},
|
special_tokens_map.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<BOS>",
|
3 |
+
"eos_token": "<EOS>",
|
4 |
+
"pad_token": "<PAD>",
|
5 |
+
"unk_token": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
}
|
12 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"eos_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"errors": "replace",
|
21 |
+
"name_or_path": "./",
|
22 |
+
"pad_token": null,
|
23 |
+
"special_tokens_map_file": null,
|
24 |
+
"tokenizer_class": "GPT2Tokenizer",
|
25 |
+
"unk_token": {
|
26 |
+
"__type": "AddedToken",
|
27 |
+
"content": "<|endoftext|>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": true,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
}
|
33 |
+
}
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|