Hugging Face's logo

tgupj
/
tiny-router

ONNX
Model card Files
xet
tgupj commited on
Commit
075f421
·
verified ·
1 Parent(s): 4289d5d

init

Browse files
Files changed (17) hide show
  1. added_tokens.json +3 -0
  2. model.pt +3 -0
  3. model_config.json +60 -0
  4. onnx/added_tokens.json +3 -0
  5. onnx/model_config.json +60 -0
  6. onnx/onnx_metadata.json +42 -0
  7. onnx/special_tokens_map.json +51 -0
  8. onnx/spm.model +3 -0
  9. onnx/temperature_scaling.json +10 -0
  10. onnx/tiny_router.int8.onnx +3 -0
  11. onnx/tiny_router.onnx +3 -0
  12. onnx/tokenizer_config.json +59 -0
  13. special_tokens_map.json +15 -0
  14. spm.model +3 -0
  15. temperature_scaling.json +10 -0
  16. tokenizer_config.json +59 -0
  17. training_args.json +26 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56812518ded8d9e6f0596b54ad9733722045eb037f2a9637454e9a282a6de975
3
+ size 565320515
model_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "encoder_name": "microsoft/deberta-v3-small",
3
+ "dropout": 0.1,
4
+ "action_vocab": [
5
+ "none",
6
+ "create",
7
+ "update",
8
+ "send",
9
+ "store",
10
+ "route",
11
+ "schedule",
12
+ "dismissed",
13
+ "clarify",
14
+ "search",
15
+ "notify",
16
+ "cancel",
17
+ "complete",
18
+ "other"
19
+ ],
20
+ "outcome_vocab": [
21
+ "success",
22
+ "pending",
23
+ "failed",
24
+ "cancelled",
25
+ "unknown"
26
+ ],
27
+ "label_maps": {
28
+ "relation_to_previous": [
29
+ "new",
30
+ "follow_up",
31
+ "correction",
32
+ "confirmation",
33
+ "cancellation",
34
+ "closure"
35
+ ],
36
+ "actionability": [
37
+ "none",
38
+ "review",
39
+ "act"
40
+ ],
41
+ "retention": [
42
+ "ephemeral",
43
+ "useful",
44
+ "remember"
45
+ ],
46
+ "urgency": [
47
+ "low",
48
+ "medium",
49
+ "high"
50
+ ]
51
+ },
52
+ "structured_hidden_dim": 32,
53
+ "recency_embed_dim": 8,
54
+ "pooling_type": "attention",
55
+ "use_head_dependencies": true,
56
+ "dependency_hidden_dim": 32,
57
+ "feature_mode": "full_interaction",
58
+ "max_length": 128,
59
+ "recency_max": 3600
60
+ }
onnx/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
onnx/model_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "encoder_name": "microsoft/deberta-v3-small",
3
+ "dropout": 0.1,
4
+ "action_vocab": [
5
+ "none",
6
+ "create",
7
+ "update",
8
+ "send",
9
+ "store",
10
+ "route",
11
+ "schedule",
12
+ "dismissed",
13
+ "clarify",
14
+ "search",
15
+ "notify",
16
+ "cancel",
17
+ "complete",
18
+ "other"
19
+ ],
20
+ "outcome_vocab": [
21
+ "success",
22
+ "pending",
23
+ "failed",
24
+ "cancelled",
25
+ "unknown"
26
+ ],
27
+ "label_maps": {
28
+ "relation_to_previous": [
29
+ "new",
30
+ "follow_up",
31
+ "correction",
32
+ "confirmation",
33
+ "cancellation",
34
+ "closure"
35
+ ],
36
+ "actionability": [
37
+ "none",
38
+ "review",
39
+ "act"
40
+ ],
41
+ "retention": [
42
+ "ephemeral",
43
+ "useful",
44
+ "remember"
45
+ ],
46
+ "urgency": [
47
+ "low",
48
+ "medium",
49
+ "high"
50
+ ]
51
+ },
52
+ "structured_hidden_dim": 32,
53
+ "recency_embed_dim": 8,
54
+ "pooling_type": "attention",
55
+ "use_head_dependencies": true,
56
+ "dependency_hidden_dim": 32,
57
+ "feature_mode": "full_interaction",
58
+ "max_length": 128,
59
+ "recency_max": 3600
60
+ }
onnx/onnx_metadata.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_file": "tiny_router.onnx",
3
+ "feature_mode": "full_interaction",
4
+ "heads": [
5
+ "relation_to_previous",
6
+ "actionability",
7
+ "retention",
8
+ "urgency"
9
+ ],
10
+ "max_length": 128,
11
+ "label_maps": {
12
+ "relation_to_previous": [
13
+ "new",
14
+ "follow_up",
15
+ "correction",
16
+ "confirmation",
17
+ "cancellation",
18
+ "closure"
19
+ ],
20
+ "actionability": [
21
+ "none",
22
+ "review",
23
+ "act"
24
+ ],
25
+ "retention": [
26
+ "ephemeral",
27
+ "useful",
28
+ "remember"
29
+ ],
30
+ "urgency": [
31
+ "low",
32
+ "medium",
33
+ "high"
34
+ ]
35
+ },
36
+ "temperature_scaling": {
37
+ "relation_to_previous": 1.333521,
38
+ "actionability": 2.113489,
39
+ "retention": 2.238721,
40
+ "urgency": 2.660725
41
+ }
42
+ }
onnx/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
onnx/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
onnx/temperature_scaling.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "method": "per_head_temperature_scaling",
3
+ "source_split": "validation",
4
+ "per_head": {
5
+ "relation_to_previous": 1.333521,
6
+ "actionability": 2.113489,
7
+ "retention": 2.238721,
8
+ "urgency": 2.660725
9
+ }
10
+ }
onnx/tiny_router.int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:772b84fa513ff63a8406ecfa031a9f61ff4ac69a4cfa259c91089a3b1133bf62
3
+ size 171758190
onnx/tiny_router.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:817549baf4f6c0531e3230124dcde592d1b8129b439d3a51fcc9f0f50c94f488
3
+ size 565782364
onnx/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "sp_model_kwargs": {},
55
+ "split_by_punct": false,
56
+ "tokenizer_class": "DebertaV2Tokenizer",
57
+ "unk_token": "[UNK]",
58
+ "vocab_type": "spm"
59
+ }
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
temperature_scaling.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "method": "per_head_temperature_scaling",
3
+ "source_split": "validation",
4
+ "per_head": {
5
+ "relation_to_previous": 1.333521,
6
+ "actionability": 2.113489,
7
+ "retention": 2.238721,
8
+ "urgency": 2.660725
9
+ }
10
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "sp_model_kwargs": {},
55
+ "split_by_punct": false,
56
+ "tokenizer_class": "DebertaV2Tokenizer",
57
+ "unk_token": "[UNK]",
58
+ "vocab_type": "spm"
59
+ }
training_args.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train_file": "data/synthetic/train.jsonl",
3
+ "validation_file": "data/synthetic/validation.jsonl",
4
+ "test_file": null,
5
+ "output_dir": "artifacts/tiny-router",
6
+ "encoder_name": "microsoft/deberta-v3-small",
7
+ "device": "auto",
8
+ "feature_mode": "full_interaction",
9
+ "pooling_type": "attention",
10
+ "use_head_dependencies": true,
11
+ "dependency_hidden_dim": 32,
12
+ "max_length": 128,
13
+ "recency_max": 3600,
14
+ "batch_size": 32,
15
+ "epochs": 20,
16
+ "encoder_lr": 2e-05,
17
+ "head_lr": 0.0001,
18
+ "weight_decay": 0.01,
19
+ "warmup_ratio": 0.1,
20
+ "dropout": 0.1,
21
+ "seed": 13,
22
+ "patience": 2,
23
+ "mixed_precision": false,
24
+ "confidence_threshold": 0.8,
25
+ "head_loss_weights": "{}"
26
+ }