maadgrom commited on
Commit
d78d445
·
verified ·
1 Parent(s): b2259f9

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 256,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "B-PARTICIPANT",
15
+ "2": "I-PARTICIPANT",
16
+ "3": "B-PRIORITY",
17
+ "4": "I-PRIORITY",
18
+ "5": "B-DATETIME",
19
+ "6": "I-DATETIME",
20
+ "7": "B-RECURRENCE",
21
+ "8": "I-RECURRENCE"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 1024,
25
+ "label2id": {
26
+ "B-DATETIME": 5,
27
+ "B-PARTICIPANT": 1,
28
+ "B-PRIORITY": 3,
29
+ "B-RECURRENCE": 7,
30
+ "I-DATETIME": 6,
31
+ "I-PARTICIPANT": 2,
32
+ "I-PRIORITY": 4,
33
+ "I-RECURRENCE": 8,
34
+ "O": 0
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "bert",
39
+ "num_attention_heads": 8,
40
+ "num_hidden_layers": 6,
41
+ "pad_token_id": 0,
42
+ "position_embedding_type": "absolute",
43
+ "transformers_version": "4.57.6",
44
+ "type_vocab_size": 2,
45
+ "use_cache": true,
46
+ "vocab_size": 30522
47
+ }
manifest.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model": "microsoft/xtremedistil-l6-h256-uncased",
3
+ "bundle_size_mb": 13.32,
4
+ "created_at": "2026-05-03T11:46:52.122552+00:00",
5
+ "files": {
6
+ "config.json": "a42323a8b73212169370a0265018350775bc8556e795c3e3348293ce877f0c26",
7
+ "onnx/model_quantized.onnx": "0b9edd8df5baa28b4a6e4e7b07c796234ab2e19280e38eb7e1705d09462f143f",
8
+ "special_tokens_map.json": "b6d346be366a7d1d48332dbc9fdf3bf8960b5d879522b7799ddba59e76237ee3",
9
+ "tokenizer.json": "79ea220416a57ca8acdf069d71875d5d2ddadef66021aeb6c120a7c546c04344",
10
+ "tokenizer_config.json": "e711904cac23112776b678356ccf702cf934babaa01125f698ac43bf9ad38e73",
11
+ "transitions.json": "ac4f0e2f0ca4dbad13ab41301354ae72dd19500299034c66fda701dcd4f8c920",
12
+ "vocab.txt": "07eced375cec144d27c900241f3e339478dec958f92fddbc551f295c992038a3"
13
+ },
14
+ "model_version": "0.1.0",
15
+ "quantization": {
16
+ "method": "dynamic",
17
+ "op_types_to_quantize": [
18
+ "MatMul",
19
+ "Gather"
20
+ ],
21
+ "per_channel": true,
22
+ "weight_type": "QInt8"
23
+ },
24
+ "quantized_source": "model_quantized.onnx",
25
+ "quantized_test_metrics": {
26
+ "DATETIME_f1": 0.6723507917174177,
27
+ "PARTICIPANT_f1": 0.8943089430894308,
28
+ "PRIORITY_f1": 0.631578947368421,
29
+ "RECURRENCE_f1": 0.7093023255813952,
30
+ "accuracy": 0.9049765258215963,
31
+ "f1": 0.7391569945021381,
32
+ "n_examples": 559,
33
+ "precision": 0.8717579250720461,
34
+ "quantization_method": "dynamic",
35
+ "recall": 0.6415694591728526
36
+ },
37
+ "runtime": {
38
+ "device": "wasm",
39
+ "dtype": "q8",
40
+ "transformers_js": "v4"
41
+ },
42
+ "schema_version": "slot-labels-v0.3.0",
43
+ "task": "token-classification",
44
+ "test_metrics": {
45
+ "base_model": "microsoft/xtremedistil-l6-h256-uncased",
46
+ "epoch": 10.0,
47
+ "seed": 42,
48
+ "test_DATETIME_f1": 0.8190854870775347,
49
+ "test_PARTICIPANT_f1": 0.920754716981132,
50
+ "test_PRIORITY_f1": 0.7979274611398963,
51
+ "test_RECURRENCE_f1": 0.8981481481481483,
52
+ "test_accuracy": 0.9550178377539941,
53
+ "test_f1": 0.853470437017995,
54
+ "test_loss": 0.6731534600257874,
55
+ "test_precision": 0.8283433133732535,
56
+ "test_recall": 0.88016967126193,
57
+ "test_runtime": 1.0824,
58
+ "test_samples_per_second": 516.459,
59
+ "test_steps_per_second": 8.315
60
+ }
61
+ }
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b9edd8df5baa28b4a6e4e7b07c796234ab2e19280e38eb7e1705d09462f143f
3
+ size 13018836
regression_metrics.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "focus_texts": [
3
+ "remind me to send the invoice to Yusuf tomorrow morning",
4
+ "book dentist appointment next Tuesday at 11",
5
+ "someday review ideas with @marta_notes"
6
+ ],
7
+ "n_cases": 3,
8
+ "n_failed": 0,
9
+ "n_passed": 3,
10
+ "results": [
11
+ {
12
+ "missing_entities": [],
13
+ "passed": true,
14
+ "predicted_entities": [
15
+ {
16
+ "group": "PARTICIPANT",
17
+ "text": "yusuf"
18
+ },
19
+ {
20
+ "group": "DATETIME",
21
+ "text": "tomorrow morning"
22
+ }
23
+ ],
24
+ "required_entities": [
25
+ {
26
+ "group": "PARTICIPANT",
27
+ "text": "Yusuf"
28
+ },
29
+ {
30
+ "group": "DATETIME",
31
+ "text": "tomorrow morning"
32
+ }
33
+ ],
34
+ "text": "remind me to send the invoice to Yusuf tomorrow morning"
35
+ },
36
+ {
37
+ "missing_entities": [],
38
+ "passed": true,
39
+ "predicted_entities": [
40
+ {
41
+ "group": "DATETIME",
42
+ "text": "next tuesday at 11"
43
+ }
44
+ ],
45
+ "required_entities": [
46
+ {
47
+ "group": "DATETIME",
48
+ "text": "next Tuesday at 11"
49
+ }
50
+ ],
51
+ "text": "book dentist appointment next Tuesday at 11"
52
+ },
53
+ {
54
+ "missing_entities": [],
55
+ "passed": true,
56
+ "predicted_entities": [
57
+ {
58
+ "group": "PRIORITY",
59
+ "text": "someday"
60
+ },
61
+ {
62
+ "group": "PARTICIPANT",
63
+ "text": "@marta_notes"
64
+ }
65
+ ],
66
+ "required_entities": [
67
+ {
68
+ "group": "PRIORITY",
69
+ "text": "someday"
70
+ },
71
+ {
72
+ "group": "PARTICIPANT",
73
+ "text": "@marta_notes"
74
+ }
75
+ ],
76
+ "text": "someday review ideas with @marta_notes"
77
+ }
78
+ ]
79
+ }
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 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
transitions.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "labels": [
3
+ "O",
4
+ "B-PARTICIPANT",
5
+ "I-PARTICIPANT",
6
+ "B-PRIORITY",
7
+ "I-PRIORITY",
8
+ "B-DATETIME",
9
+ "I-DATETIME",
10
+ "B-RECURRENCE",
11
+ "I-RECURRENCE"
12
+ ],
13
+ "log_transitions": [
14
+ [
15
+ -0.21329336044444958,
16
+ -2.395360318337538,
17
+ -37.78172024711259,
18
+ -5.113746528770403,
19
+ -37.78172024711259,
20
+ -2.4165778278557335,
21
+ -37.78172024711259,
22
+ -5.167092509475696,
23
+ -37.78172024711259
24
+ ],
25
+ [
26
+ -1.9565559334666265,
27
+ -7.683403681052827,
28
+ -1.293163013988475,
29
+ -1.5653064830124768,
30
+ -35.31442479698237,
31
+ -1.4200054184622015,
32
+ -35.31442479698237,
33
+ -2.016976992941391,
34
+ -35.31442479698237
35
+ ],
36
+ [
37
+ -0.7998719529095837,
38
+ -4.688285092698433,
39
+ -1.770514360614312,
40
+ -2.2173646848853252,
41
+ -34.1110656778552,
42
+ -1.9261676703261035,
43
+ -34.1110656778552,
44
+ -2.1493112216403105,
45
+ -34.1110656778552
46
+ ],
47
+ [
48
+ -2.5018849863224055,
49
+ -6.792344427469811,
50
+ -34.423365543399356,
51
+ -6.792344427469811,
52
+ -0.4122218905710442,
53
+ -2.249049645200796,
54
+ -34.423365543399356,
55
+ -1.9095425048844321,
56
+ -34.423365543399356
57
+ ],
58
+ [
59
+ -2.1546649629174146,
60
+ -6.799055862057797,
61
+ -34.43007697798734,
62
+ -6.799055862057797,
63
+ -0.8432184925939632,
64
+ -1.6229061294849618,
65
+ -34.43007697798734,
66
+ -1.3697102331043514,
67
+ -34.43007697798734
68
+ ],
69
+ [
70
+ -1.7336909992051686,
71
+ -7.0015491582681655,
72
+ -35.73118256286516,
73
+ -6.490723534502308,
74
+ -35.73118256286516,
75
+ -4.544813385447166,
76
+ -0.21370417595891933,
77
+ -5.902936869600278,
78
+ -35.73118256286516
79
+ ],
80
+ [
81
+ -1.570300746704473,
82
+ -8.211482916444066,
83
+ -35.84250403237361,
84
+ -3.8676774945913692,
85
+ -35.84250403237361,
86
+ -4.260239197863619,
87
+ -0.3115875933053358,
88
+ -3.71167324611479,
89
+ -35.84250403237361
90
+ ],
91
+ [
92
+ -2.4161263407420552,
93
+ -6.846943139584381,
94
+ -34.477964255513925,
95
+ -5.460648778465241,
96
+ -34.477964255513925,
97
+ -2.5984478975360075,
98
+ -34.477964255513925,
99
+ -6.846943139584381,
100
+ -0.18636798974569402
101
+ ],
102
+ [
103
+ -2.919795707464039,
104
+ -7.301822342136933,
105
+ -34.93284345806648,
106
+ -4.257299904414462,
107
+ -34.93284345806648,
108
+ -1.1684242991412823,
109
+ -34.93284345806648,
110
+ -7.301822342136933,
111
+ -0.4785362197822449
112
+ ]
113
+ ]
114
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff