Upload folder using huggingface_hub
Browse files- added_tokens.json +5 -0
- config.json +3 -0
- gliner_config.json +35 -0
- onnx/model.onnx +3 -0
- onnx/model_bnb4.onnx +3 -0
- onnx/model_fp16.onnx +3 -0
- onnx/model_int8.onnx +3 -0
- onnx/model_q4.onnx +3 -0
- onnx/model_q4f16.onnx +3 -0
- onnx/model_quantized.onnx +3 -0
- onnx/model_uint8.onnx +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +82 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<<ENT>>": 31103,
|
3 |
+
"<<SEP>>": 31104,
|
4 |
+
"[FLERT]": 31102
|
5 |
+
}
|
config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_type": "gliner"
|
3 |
+
}
|
gliner_config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"class_token_index": 31103,
|
3 |
+
"dropout": 0.4,
|
4 |
+
"encoder_config": null,
|
5 |
+
"ent_token": "<<ENT>>",
|
6 |
+
"eval_every": 900000,
|
7 |
+
"fine_tune": true,
|
8 |
+
"has_rnn": true,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"log_dir": "logs",
|
11 |
+
"lr_encoder": "1e-5",
|
12 |
+
"lr_others": "5e-5",
|
13 |
+
"max_len": 384,
|
14 |
+
"max_neg_type_ratio": 1,
|
15 |
+
"max_types": 25,
|
16 |
+
"max_width": 10,
|
17 |
+
"model_name": "dbmdz/bert-base-italian-xxl-cased",
|
18 |
+
"model_type": "gliner",
|
19 |
+
"name": "large",
|
20 |
+
"num_steps": 100000,
|
21 |
+
"prev_path": "none",
|
22 |
+
"random_drop": true,
|
23 |
+
"root_dir": "ablation_backbone",
|
24 |
+
"sep_token": "<<SEP>>",
|
25 |
+
"shuffle_types": true,
|
26 |
+
"size_sup": -1,
|
27 |
+
"span_mode": "marker",
|
28 |
+
"subtoken_pooling": "first",
|
29 |
+
"train_batch_size": 8,
|
30 |
+
"train_data": "dataset/train.json",
|
31 |
+
"transformers_version": "4.38.2",
|
32 |
+
"vocab_size": 31105,
|
33 |
+
"warmup_ratio": 0.1,
|
34 |
+
"words_splitter_type": "whitespace"
|
35 |
+
}
|
onnx/model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:046b483bc552a4b6da46ffefcf589ffcca1e26769fa2e48dbb0afc3262c10045
|
3 |
+
size 494481258
|
onnx/model_bnb4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e40c843db17fec2378607ae38e477eb99bb6418e83fafa18b716eec082736f76
|
3 |
+
size 172006696
|
onnx/model_fp16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4d6ce75a62b473de308cfa45466e36678c61b32f996ae40873a339058f2af6c
|
3 |
+
size 247623730
|
onnx/model_int8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f488c30f01815cbe773990bbfb3a807b671b1e482e2542050bf7d218bd32443
|
3 |
+
size 124655682
|
onnx/model_q4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e40c843db17fec2378607ae38e477eb99bb6418e83fafa18b716eec082736f76
|
3 |
+
size 172006696
|
onnx/model_q4f16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37ad1cb374e0c7ecf9ac1b5e1604d45dd9e6287e60f7f402d0c72b2e9362a4da
|
3 |
+
size 110259033
|
onnx/model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f488c30f01815cbe773990bbfb3a807b671b1e482e2542050bf7d218bd32443
|
3 |
+
size 124655682
|
onnx/model_uint8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43d2eed2d70d1109d72e74d303766d5cec4a498378141f793eca2fc937a0949c
|
3 |
+
size 124655723
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
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 |
+
"101": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"102": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"103": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"104": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"31102": {
|
44 |
+
"content": "[FLERT]",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": true,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": false
|
50 |
+
},
|
51 |
+
"31103": {
|
52 |
+
"content": "<<ENT>>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": true,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": false
|
58 |
+
},
|
59 |
+
"31104": {
|
60 |
+
"content": "<<SEP>>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": true,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": false
|
66 |
+
}
|
67 |
+
},
|
68 |
+
"clean_up_tokenization_spaces": true,
|
69 |
+
"cls_token": "[CLS]",
|
70 |
+
"do_basic_tokenize": true,
|
71 |
+
"do_lower_case": false,
|
72 |
+
"mask_token": "[MASK]",
|
73 |
+
"max_len": 512,
|
74 |
+
"model_max_length": 512,
|
75 |
+
"never_split": null,
|
76 |
+
"pad_token": "[PAD]",
|
77 |
+
"sep_token": "[SEP]",
|
78 |
+
"strip_accents": null,
|
79 |
+
"tokenize_chinese_chars": true,
|
80 |
+
"tokenizer_class": "BertTokenizer",
|
81 |
+
"unk_token": "[UNK]"
|
82 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|