PereLluis13
commited on
Commit
•
5b086db
1
Parent(s):
bf48b36
Automatic push from sapienzanlp
Browse files- added_tokens.json +28 -0
- config.json +15 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +36 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +44 -0
added_tokens.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"--NME--": 128001,
|
3 |
+
"[MASK]": 128000,
|
4 |
+
"[R-0]": 128002,
|
5 |
+
"[R-10]": 128012,
|
6 |
+
"[R-11]": 128013,
|
7 |
+
"[R-12]": 128014,
|
8 |
+
"[R-13]": 128015,
|
9 |
+
"[R-14]": 128016,
|
10 |
+
"[R-15]": 128017,
|
11 |
+
"[R-16]": 128018,
|
12 |
+
"[R-17]": 128019,
|
13 |
+
"[R-18]": 128020,
|
14 |
+
"[R-19]": 128021,
|
15 |
+
"[R-1]": 128003,
|
16 |
+
"[R-20]": 128022,
|
17 |
+
"[R-21]": 128023,
|
18 |
+
"[R-22]": 128024,
|
19 |
+
"[R-23]": 128025,
|
20 |
+
"[R-2]": 128004,
|
21 |
+
"[R-3]": 128005,
|
22 |
+
"[R-4]": 128006,
|
23 |
+
"[R-5]": 128007,
|
24 |
+
"[R-6]": 128008,
|
25 |
+
"[R-7]": 128009,
|
26 |
+
"[R-8]": 128010,
|
27 |
+
"[R-9]": 128011
|
28 |
+
}
|
config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation": "gelu",
|
3 |
+
"additional_special_symbols": 25,
|
4 |
+
"architectures": [
|
5 |
+
"RelikReaderREModel"
|
6 |
+
],
|
7 |
+
"linears_hidden_size": 512,
|
8 |
+
"model_type": "relik_reader",
|
9 |
+
"num_layers": null,
|
10 |
+
"torch_dtype": "float32",
|
11 |
+
"training": false,
|
12 |
+
"transformer_model": "microsoft/deberta-v3-small",
|
13 |
+
"transformers_version": "4.33.3",
|
14 |
+
"use_last_k_layers": 1
|
15 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d3fba553d7cf83e04f45d7c53063518be3f52f61739d24f223280ad56c68c29
|
3 |
+
size 583740837
|
special_tokens_map.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"--NME--",
|
4 |
+
"[R-0]",
|
5 |
+
"[R-1]",
|
6 |
+
"[R-2]",
|
7 |
+
"[R-3]",
|
8 |
+
"[R-4]",
|
9 |
+
"[R-5]",
|
10 |
+
"[R-6]",
|
11 |
+
"[R-7]",
|
12 |
+
"[R-8]",
|
13 |
+
"[R-9]",
|
14 |
+
"[R-10]",
|
15 |
+
"[R-11]",
|
16 |
+
"[R-12]",
|
17 |
+
"[R-13]",
|
18 |
+
"[R-14]",
|
19 |
+
"[R-15]",
|
20 |
+
"[R-16]",
|
21 |
+
"[R-17]",
|
22 |
+
"[R-18]",
|
23 |
+
"[R-19]",
|
24 |
+
"[R-20]",
|
25 |
+
"[R-21]",
|
26 |
+
"[R-22]",
|
27 |
+
"[R-23]"
|
28 |
+
],
|
29 |
+
"bos_token": "[CLS]",
|
30 |
+
"cls_token": "[CLS]",
|
31 |
+
"eos_token": "[SEP]",
|
32 |
+
"mask_token": "[MASK]",
|
33 |
+
"pad_token": "[PAD]",
|
34 |
+
"sep_token": "[SEP]",
|
35 |
+
"unk_token": "[UNK]"
|
36 |
+
}
|
spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
3 |
+
size 2464616
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"additional_special_tokens": [
|
4 |
+
"--NME--",
|
5 |
+
"[R-0]",
|
6 |
+
"[R-1]",
|
7 |
+
"[R-2]",
|
8 |
+
"[R-3]",
|
9 |
+
"[R-4]",
|
10 |
+
"[R-5]",
|
11 |
+
"[R-6]",
|
12 |
+
"[R-7]",
|
13 |
+
"[R-8]",
|
14 |
+
"[R-9]",
|
15 |
+
"[R-10]",
|
16 |
+
"[R-11]",
|
17 |
+
"[R-12]",
|
18 |
+
"[R-13]",
|
19 |
+
"[R-14]",
|
20 |
+
"[R-15]",
|
21 |
+
"[R-16]",
|
22 |
+
"[R-17]",
|
23 |
+
"[R-18]",
|
24 |
+
"[R-19]",
|
25 |
+
"[R-20]",
|
26 |
+
"[R-21]",
|
27 |
+
"[R-22]",
|
28 |
+
"[R-23]"
|
29 |
+
],
|
30 |
+
"bos_token": "[CLS]",
|
31 |
+
"clean_up_tokenization_spaces": true,
|
32 |
+
"cls_token": "[CLS]",
|
33 |
+
"do_lower_case": false,
|
34 |
+
"eos_token": "[SEP]",
|
35 |
+
"mask_token": "[MASK]",
|
36 |
+
"model_max_length": 1000000000000000019884624838656,
|
37 |
+
"pad_token": "[PAD]",
|
38 |
+
"sep_token": "[SEP]",
|
39 |
+
"sp_model_kwargs": {},
|
40 |
+
"split_by_punct": false,
|
41 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
42 |
+
"unk_token": "[UNK]",
|
43 |
+
"vocab_type": "spm"
|
44 |
+
}
|