Hugging Face's logo

WhiteRoomProdigy
/
amicus-ner-v1

Token Classification
Transformers
ONNX
Safetensors
English
bert
ner
legal
legal-bert
nigerian-law
Model card Files
xet
 Community
WhiteRoomProdigy commited on
Commit
fbf174d
·
verified ·
1 Parent(s): e651658

Add ONNX (CPU-optimised) model

Browse files
Files changed (15) hide show
  1. onnx/config.json +64 -0
  2. onnx/model.onnx +3 -0
  3. onnx/model_optimized.onnx +3 -0
  4. onnx/ort_config.json +35 -0
  5. onnx/quantized/config.json +64 -0
  6. onnx/quantized/model_quantized.onnx +3 -0
  7. onnx/quantized/ort_config.json +33 -0
  8. onnx/quantized/special_tokens_map.json +37 -0
  9. onnx/quantized/tokenizer.json +0 -0
  10. onnx/quantized/tokenizer_config.json +62 -0
  11. onnx/quantized/vocab.txt +0 -0
  12. onnx/special_tokens_map.json +37 -0
  13. onnx/tokenizer.json +0 -0
  14. onnx/tokenizer_config.json +62 -0
  15. onnx/vocab.txt +0 -0
onnx/config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "eos_token_ids": 0,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "B-CASE_NAME",
15
+ "2": "I-CASE_NAME",
16
+ "3": "B-CITATION",
17
+ "4": "I-CITATION",
18
+ "5": "B-STATUTE",
19
+ "6": "I-STATUTE",
20
+ "7": "B-COURT",
21
+ "8": "I-COURT",
22
+ "9": "B-DATE",
23
+ "10": "I-DATE",
24
+ "11": "B-JUDGE",
25
+ "12": "I-JUDGE",
26
+ "13": "B-RATIO",
27
+ "14": "I-RATIO",
28
+ "15": "B-HELD",
29
+ "16": "I-HELD"
30
+ },
31
+ "initializer_range": 0.02,
32
+ "intermediate_size": 3072,
33
+ "label2id": {
34
+ "B-CASE_NAME": 1,
35
+ "B-CITATION": 3,
36
+ "B-COURT": 7,
37
+ "B-DATE": 9,
38
+ "B-HELD": 15,
39
+ "B-JUDGE": 11,
40
+ "B-RATIO": 13,
41
+ "B-STATUTE": 5,
42
+ "I-CASE_NAME": 2,
43
+ "I-CITATION": 4,
44
+ "I-COURT": 8,
45
+ "I-DATE": 10,
46
+ "I-HELD": 16,
47
+ "I-JUDGE": 12,
48
+ "I-RATIO": 14,
49
+ "I-STATUTE": 6,
50
+ "O": 0
51
+ },
52
+ "layer_norm_eps": 1e-12,
53
+ "max_position_embeddings": 512,
54
+ "model_type": "bert",
55
+ "num_attention_heads": 12,
56
+ "num_hidden_layers": 12,
57
+ "output_past": true,
58
+ "pad_token_id": 0,
59
+ "position_embedding_type": "absolute",
60
+ "transformers_version": "4.57.6",
61
+ "type_vocab_size": 2,
62
+ "use_cache": true,
63
+ "vocab_size": 30522
64
+ }
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:628d140d9ab3ccebea40d271ca4928d89abfd3b6a2b16782f3f9b85ce1a0be89
3
+ size 435828706
onnx/model_optimized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb42f569256e13be1c4a502de4f51ca5587d22d397e52cb692817bb11689747e
3
+ size 435657387
onnx/ort_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "one_external_file": true,
3
+ "opset": null,
4
+ "optimization": {
5
+ "disable_attention_fusion": false,
6
+ "disable_bias_add_fusion": false,
7
+ "disable_bias_gelu_fusion": false,
8
+ "disable_bias_skip_layer_norm_fusion": false,
9
+ "disable_bias_splitgelu_fusion": false,
10
+ "disable_embed_layer_norm_fusion": true,
11
+ "disable_gelu_fusion": false,
12
+ "disable_group_norm_fusion": true,
13
+ "disable_layer_norm_fusion": false,
14
+ "disable_nhwc_conv": false,
15
+ "disable_packed_kv": true,
16
+ "disable_packed_qkv": false,
17
+ "disable_rotary_embeddings": false,
18
+ "disable_shape_inference": false,
19
+ "disable_skip_group_norm_fusion": false,
20
+ "disable_skip_layer_norm_fusion": false,
21
+ "enable_gelu_approximation": false,
22
+ "enable_gemm_fast_gelu_fusion": false,
23
+ "enable_transformers_specific_optimizations": true,
24
+ "fp16": false,
25
+ "no_attention_mask": false,
26
+ "optimization_level": 99,
27
+ "optimize_for_gpu": false,
28
+ "use_group_norm_channels_first": false,
29
+ "use_mask_index": false,
30
+ "use_multi_head_attention": false,
31
+ "use_raw_attention_mask": false
32
+ },
33
+ "quantization": {},
34
+ "use_external_data_format": false
35
+ }
onnx/quantized/config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "eos_token_ids": 0,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "B-CASE_NAME",
15
+ "2": "I-CASE_NAME",
16
+ "3": "B-CITATION",
17
+ "4": "I-CITATION",
18
+ "5": "B-STATUTE",
19
+ "6": "I-STATUTE",
20
+ "7": "B-COURT",
21
+ "8": "I-COURT",
22
+ "9": "B-DATE",
23
+ "10": "I-DATE",
24
+ "11": "B-JUDGE",
25
+ "12": "I-JUDGE",
26
+ "13": "B-RATIO",
27
+ "14": "I-RATIO",
28
+ "15": "B-HELD",
29
+ "16": "I-HELD"
30
+ },
31
+ "initializer_range": 0.02,
32
+ "intermediate_size": 3072,
33
+ "label2id": {
34
+ "B-CASE_NAME": 1,
35
+ "B-CITATION": 3,
36
+ "B-COURT": 7,
37
+ "B-DATE": 9,
38
+ "B-HELD": 15,
39
+ "B-JUDGE": 11,
40
+ "B-RATIO": 13,
41
+ "B-STATUTE": 5,
42
+ "I-CASE_NAME": 2,
43
+ "I-CITATION": 4,
44
+ "I-COURT": 8,
45
+ "I-DATE": 10,
46
+ "I-HELD": 16,
47
+ "I-JUDGE": 12,
48
+ "I-RATIO": 14,
49
+ "I-STATUTE": 6,
50
+ "O": 0
51
+ },
52
+ "layer_norm_eps": 1e-12,
53
+ "max_position_embeddings": 512,
54
+ "model_type": "bert",
55
+ "num_attention_heads": 12,
56
+ "num_hidden_layers": 12,
57
+ "output_past": true,
58
+ "pad_token_id": 0,
59
+ "position_embedding_type": "absolute",
60
+ "transformers_version": "4.57.6",
61
+ "type_vocab_size": 2,
62
+ "use_cache": true,
63
+ "vocab_size": 30522
64
+ }
onnx/quantized/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7336fe775f82930987f6de1f65ef7a9065d15991872a41cb55a30ac31768fde1
3
+ size 109697729
onnx/quantized/ort_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "one_external_file": true,
3
+ "opset": null,
4
+ "optimization": {},
5
+ "quantization": {
6
+ "activations_dtype": "QUInt8",
7
+ "activations_symmetric": false,
8
+ "format": "QOperator",
9
+ "is_static": false,
10
+ "mode": "IntegerOps",
11
+ "nodes_to_exclude": [],
12
+ "nodes_to_quantize": [],
13
+ "operators_to_quantize": [
14
+ "Conv",
15
+ "MatMul",
16
+ "Attention",
17
+ "LSTM",
18
+ "Gather",
19
+ "Transpose",
20
+ "EmbedLayerNormalization"
21
+ ],
22
+ "per_channel": false,
23
+ "qdq_add_pair_to_weight": false,
24
+ "qdq_dedicated_pair": false,
25
+ "qdq_op_type_per_channel_support_to_axis": {
26
+ "MatMul": 1
27
+ },
28
+ "reduce_range": false,
29
+ "weights_dtype": "QInt8",
30
+ "weights_symmetric": true
31
+ },
32
+ "use_external_data_format": false
33
+ }
onnx/quantized/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
+ }
onnx/quantized/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
onnx/quantized/tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "max_length": 256,
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "stride": 0,
56
+ "strip_accents": null,
57
+ "tokenize_chinese_chars": true,
58
+ "tokenizer_class": "BertTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "[UNK]"
62
+ }
onnx/quantized/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
onnx/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
+ }
onnx/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
onnx/tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "max_length": 256,
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "stride": 0,
56
+ "strip_accents": null,
57
+ "tokenize_chinese_chars": true,
58
+ "tokenizer_class": "BertTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "[UNK]"
62
+ }
onnx/vocab.txt ADDED
The diff for this file is too large to render. See raw diff