Update tiny models for PersimmonForSequenceClassification
#7
by
hf-transformers-bot
- opened
- added_tokens.json +4 -0
- pytorch_model.bin +1 -1
- special_tokens_map.json +2 -14
- tokenizer.json +2 -2
- tokenizer_config.json +22 -16
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<unk>": 0,
|
3 |
+
"|ENDOFTEXT|": 71013
|
4 |
+
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 33620317
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:238ab312145e1e8b2bb0ffd8c2451b658f72dee0828f2dbcc10a1659e6c0235d
|
3 |
size 33620317
|
special_tokens_map.json
CHANGED
@@ -1,16 +1,4 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": true,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"unk_token": {
|
10 |
-
"content": "<unk>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": true,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
}
|
16 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "|ENDOFTEXT|",
|
3 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
}
|
tokenizer.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c624be2d9dddae3e8c82cda48fe5c737ec6710225e953ef851a4023f2d4796a
|
3 |
+
size 16464051
|
tokenizer_config.json
CHANGED
@@ -1,29 +1,35 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
-
"
|
5 |
-
"
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
},
|
|
|
|
|
12 |
"clean_up_tokenization_spaces": false,
|
13 |
"eos_token": null,
|
14 |
-
"legacy":
|
15 |
"model_max_length": 512,
|
16 |
"pad_token": null,
|
17 |
"sp_model_kwargs": {},
|
18 |
"spaces_between_special_tokens": false,
|
19 |
"tokenizer_class": "LlamaTokenizer",
|
20 |
-
"
|
21 |
-
|
22 |
-
"content": "<unk>",
|
23 |
-
"lstrip": false,
|
24 |
-
"normalized": true,
|
25 |
-
"rstrip": false,
|
26 |
-
"single_word": false
|
27 |
-
},
|
28 |
"use_default_system_prompt": true
|
29 |
}
|
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"71013": {
|
14 |
+
"content": "|ENDOFTEXT|",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
}
|
21 |
},
|
22 |
+
"additional_special_tokens": [],
|
23 |
+
"bos_token": "|ENDOFTEXT|",
|
24 |
"clean_up_tokenization_spaces": false,
|
25 |
"eos_token": null,
|
26 |
+
"legacy": true,
|
27 |
"model_max_length": 512,
|
28 |
"pad_token": null,
|
29 |
"sp_model_kwargs": {},
|
30 |
"spaces_between_special_tokens": false,
|
31 |
"tokenizer_class": "LlamaTokenizer",
|
32 |
+
"tokenizer_file": null,
|
33 |
+
"unk_token": "<unk>",
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
"use_default_system_prompt": true
|
35 |
}
|