Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- config.json +84 -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
- quantize_config.json +17 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +63 -0
- vocab.txt +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
vocab.txt filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dicta-il/dictabert-ner",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "B-ANG",
|
14 |
+
"1": "B-DUC",
|
15 |
+
"2": "B-EVE",
|
16 |
+
"3": "B-FAC",
|
17 |
+
"4": "B-GPE",
|
18 |
+
"5": "B-LOC",
|
19 |
+
"6": "B-ORG",
|
20 |
+
"7": "B-PER",
|
21 |
+
"8": "B-WOA",
|
22 |
+
"9": "B-INFORMAL",
|
23 |
+
"10": "B-MISC",
|
24 |
+
"11": "B-TIMEX",
|
25 |
+
"12": "B-TTL",
|
26 |
+
"13": "I-DUC",
|
27 |
+
"14": "I-EVE",
|
28 |
+
"15": "I-FAC",
|
29 |
+
"16": "I-GPE",
|
30 |
+
"17": "I-LOC",
|
31 |
+
"18": "I-ORG",
|
32 |
+
"19": "I-PER",
|
33 |
+
"20": "I-WOA",
|
34 |
+
"21": "I-ANG",
|
35 |
+
"22": "I-INFORMAL",
|
36 |
+
"23": "I-MISC",
|
37 |
+
"24": "I-TIMEX",
|
38 |
+
"25": "I-TTL",
|
39 |
+
"26": "O"
|
40 |
+
},
|
41 |
+
"initializer_range": 0.02,
|
42 |
+
"intermediate_size": 3072,
|
43 |
+
"label2id": {
|
44 |
+
"B-ANG": 0,
|
45 |
+
"B-DUC": 1,
|
46 |
+
"B-EVE": 2,
|
47 |
+
"B-FAC": 3,
|
48 |
+
"B-GPE": 4,
|
49 |
+
"B-INFORMAL": 9,
|
50 |
+
"B-LOC": 5,
|
51 |
+
"B-MISC": 10,
|
52 |
+
"B-ORG": 6,
|
53 |
+
"B-PER": 7,
|
54 |
+
"B-TIMEX": 11,
|
55 |
+
"B-TTL": 12,
|
56 |
+
"B-WOA": 8,
|
57 |
+
"I-ANG": 21,
|
58 |
+
"I-DUC": 13,
|
59 |
+
"I-EVE": 14,
|
60 |
+
"I-FAC": 15,
|
61 |
+
"I-GPE": 16,
|
62 |
+
"I-INFORMAL": 22,
|
63 |
+
"I-LOC": 17,
|
64 |
+
"I-MISC": 23,
|
65 |
+
"I-ORG": 18,
|
66 |
+
"I-PER": 19,
|
67 |
+
"I-TIMEX": 24,
|
68 |
+
"I-TTL": 25,
|
69 |
+
"I-WOA": 20,
|
70 |
+
"O": 26
|
71 |
+
},
|
72 |
+
"layer_norm_eps": 1e-12,
|
73 |
+
"max_position_embeddings": 512,
|
74 |
+
"model_type": "bert",
|
75 |
+
"newmodern": true,
|
76 |
+
"num_attention_heads": 12,
|
77 |
+
"num_hidden_layers": 12,
|
78 |
+
"pad_token_id": 0,
|
79 |
+
"position_embedding_type": "absolute",
|
80 |
+
"transformers_version": "4.43.4",
|
81 |
+
"type_vocab_size": 2,
|
82 |
+
"use_cache": true,
|
83 |
+
"vocab_size": 128000
|
84 |
+
}
|
onnx/model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a54be1ee450f180993edf932a1c257f644717f31ac884954bb13ff617feea7f7
|
3 |
+
size 735437154
|
onnx/model_bnb4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09487755b0570f7fb7c6495d4bb0242bc197c0054b1667018b8e392992eb8fe3
|
3 |
+
size 443414349
|
onnx/model_fp16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:845040b6ffb613bbb2653f7f52e64eb7c323eda13be92d7c6b339361cf037b36
|
3 |
+
size 367885895
|
onnx/model_int8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd7ac841768f11197e1d46ea6bbfe82d9cd9e21289be8761af63dbc996a32007
|
3 |
+
size 184984466
|
onnx/model_q4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:225a4209cfb4c11d0b024ec85c64e7c7b4327fdebae9b3cec29107b04179f7a6
|
3 |
+
size 448723525
|
onnx/model_q4f16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cd1d81be1c7043959d37711dad49962147073a9adc84adb0007c18237b09ec8
|
3 |
+
size 245773433
|
onnx/model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd7ac841768f11197e1d46ea6bbfe82d9cd9e21289be8761af63dbc996a32007
|
3 |
+
size 184984466
|
onnx/model_uint8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e822a39c03add6a3c334253688d1d2bc16cbecc55072056fa6fc89bdb582e57
|
3 |
+
size 184984466
|
quantize_config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"modes": [
|
3 |
+
"fp16",
|
4 |
+
"q8",
|
5 |
+
"int8",
|
6 |
+
"uint8",
|
7 |
+
"q4",
|
8 |
+
"q4f16",
|
9 |
+
"bnb4"
|
10 |
+
],
|
11 |
+
"per_channel": true,
|
12 |
+
"reduce_range": true,
|
13 |
+
"block_size": null,
|
14 |
+
"is_symmetric": true,
|
15 |
+
"accuracy_level": null,
|
16 |
+
"quant_type": 1
|
17 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[UNK]",
|
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": "[PAD]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"5": {
|
44 |
+
"content": "[BLANK]",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
}
|
51 |
+
},
|
52 |
+
"clean_up_tokenization_spaces": true,
|
53 |
+
"cls_token": "[CLS]",
|
54 |
+
"do_lower_case": true,
|
55 |
+
"mask_token": "[MASK]",
|
56 |
+
"model_max_length": 512,
|
57 |
+
"pad_token": "[PAD]",
|
58 |
+
"sep_token": "[SEP]",
|
59 |
+
"strip_accents": null,
|
60 |
+
"tokenize_chinese_chars": true,
|
61 |
+
"tokenizer_class": "BertTokenizer",
|
62 |
+
"unk_token": "[UNK]"
|
63 |
+
}
|
vocab.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fb90bfa35244d26f0065d1fcd0b5becc3da3d44d616a7e2aacaf6320b9fa2d0
|
3 |
+
size 1500244
|