Upload folder using huggingface_hub
Browse files- added_tokens.json +6 -0
- config.json +3 -0
- gliner_config.json +31 -0
- onnx/model.onnx +3 -0
- onnx/model_q4.onnx +3 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +82 -0
added_tokens.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<<ENT>>": 128002,
|
3 |
+
"<<SEP>>": 128003,
|
4 |
+
"[FLERT]": 128001,
|
5 |
+
"[MASK]": 128000
|
6 |
+
}
|
config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_type": "gliner"
|
3 |
+
}
|
gliner_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"class_token_index": 128002,
|
3 |
+
"dropout": 0.4,
|
4 |
+
"encoder_config": null,
|
5 |
+
"ent_token": "<<ENT>>",
|
6 |
+
"eval_every": 5000,
|
7 |
+
"fine_tune": true,
|
8 |
+
"has_rnn": true,
|
9 |
+
"hidden_size": 512,
|
10 |
+
"lr_encoder": "1e-5",
|
11 |
+
"lr_others": "5e-5",
|
12 |
+
"max_len": 300,
|
13 |
+
"max_neg_type_ratio": 1,
|
14 |
+
"max_types": 25,
|
15 |
+
"max_width": 12,
|
16 |
+
"model_name": "microsoft/deberta-v3-large",
|
17 |
+
"model_type": "gliner",
|
18 |
+
"name": "correct",
|
19 |
+
"num_steps": 30000,
|
20 |
+
"random_drop": true,
|
21 |
+
"sep_token": "<<SEP>>",
|
22 |
+
"shuffle_types": true,
|
23 |
+
"size_sup": -1,
|
24 |
+
"span_mode": "markerV0",
|
25 |
+
"subtoken_pooling": "first",
|
26 |
+
"train_batch_size": 8,
|
27 |
+
"transformers_version": "4.38.2",
|
28 |
+
"vocab_size": 128004,
|
29 |
+
"warmup_ratio": 3000,
|
30 |
+
"words_splitter_type": "whitespace"
|
31 |
+
}
|
onnx/model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fdfc25cb2a1dc8df65679d5663c62753c79a1f7f42a432a5576de26bdf411f0
|
3 |
+
size 1784460603
|
onnx/model_q4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:350d91b9e9ccefc9bfc1b492c2eb79e5981c727028a2ea8713da9b67a165624a
|
3 |
+
size 932976268
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"unk_token": {
|
9 |
+
"content": "[UNK]",
|
10 |
+
"lstrip": false,
|
11 |
+
"normalized": true,
|
12 |
+
"rstrip": false,
|
13 |
+
"single_word": false
|
14 |
+
}
|
15 |
+
}
|
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 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[CLS]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[SEP]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[UNK]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"128000": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"128001": {
|
44 |
+
"content": "[FLERT]",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": true,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": false
|
50 |
+
},
|
51 |
+
"128002": {
|
52 |
+
"content": "<<ENT>>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": true,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": false
|
58 |
+
},
|
59 |
+
"128003": {
|
60 |
+
"content": "<<SEP>>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": true,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": false
|
66 |
+
}
|
67 |
+
},
|
68 |
+
"bos_token": "[CLS]",
|
69 |
+
"clean_up_tokenization_spaces": true,
|
70 |
+
"cls_token": "[CLS]",
|
71 |
+
"do_lower_case": false,
|
72 |
+
"eos_token": "[SEP]",
|
73 |
+
"mask_token": "[MASK]",
|
74 |
+
"model_max_length": 1000000000000000019884624838656,
|
75 |
+
"pad_token": "[PAD]",
|
76 |
+
"sep_token": "[SEP]",
|
77 |
+
"sp_model_kwargs": {},
|
78 |
+
"split_by_punct": false,
|
79 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
80 |
+
"unk_token": "[UNK]",
|
81 |
+
"vocab_type": "spm"
|
82 |
+
}
|