Hugging Face's logo

Ashybalka
/
xlm-roberta-taxonomy-sales-de

Text Classification
Transformers
ONNX
Safetensors
German
xlm-roberta
job-classification
german
sales-classification
taxonomy-sales
text-embeddings-inference
Model card Files
xet
 Community
1
Ashybalka commited on
Commit
3c0613a
·
verified ·
1 Parent(s): b27bbf4

Upload model artifacts (11 files)

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. classification_report.txt +14 -0
  3. config.json +47 -0
  4. onnx-int8/model_quantized.onnx +3 -0
  5. onnx/model.onnx +3 -0
  6. pytorch/config.json +47 -0
  7. pytorch/model.safetensors +3 -0
  8. sentencepiece.bpe.model +3 -0
  9. special_tokens_map.json +15 -0
  10. test_metrics.json +5 -0
  11. tokenizer.json +3 -0
  12. tokenizer_config.json +55 -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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
classification_report.txt ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ precision recall f1-score support
2
+
3
+ Business Development & Strategic Sales 0.852 0.868 0.860 53
4
+ Field Sales & Outside Sales 0.925 0.876 0.900 226
5
+ Inside Sales & Telesales 0.951 0.879 0.913 132
6
+ Key Account & Account Management 0.879 0.892 0.885 65
7
+ Retail & Store Sales 0.982 0.982 0.982 500
8
+ Sales Management & Leadership 0.760 0.864 0.809 44
9
+ Sales Operations & Support 0.759 0.936 0.838 47
10
+ Technical Sales & Sales Engineering 0.824 0.875 0.848 48
11
+
12
+ accuracy 0.926 1115
13
+ macro avg 0.866 0.896 0.879 1115
14
+ weighted avg 0.930 0.926 0.927 1115
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "dtype": "float32",
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "Business Development & Strategic Sales",
15
+ "1": "Field Sales & Outside Sales",
16
+ "2": "Inside Sales & Telesales",
17
+ "3": "Key Account & Account Management",
18
+ "4": "Retail & Store Sales",
19
+ "5": "Sales Management & Leadership",
20
+ "6": "Sales Operations & Support",
21
+ "7": "Technical Sales & Sales Engineering"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "Business Development & Strategic Sales": 0,
27
+ "Field Sales & Outside Sales": 1,
28
+ "Inside Sales & Telesales": 2,
29
+ "Key Account & Account Management": 3,
30
+ "Retail & Store Sales": 4,
31
+ "Sales Management & Leadership": 5,
32
+ "Sales Operations & Support": 6,
33
+ "Technical Sales & Sales Engineering": 7
34
+ },
35
+ "layer_norm_eps": 1e-05,
36
+ "max_position_embeddings": 514,
37
+ "model_type": "xlm-roberta",
38
+ "num_attention_heads": 12,
39
+ "num_hidden_layers": 12,
40
+ "output_past": true,
41
+ "pad_token_id": 1,
42
+ "position_embedding_type": "absolute",
43
+ "transformers_version": "4.57.6",
44
+ "type_vocab_size": 1,
45
+ "use_cache": true,
46
+ "vocab_size": 250002
47
+ }
onnx-int8/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76240033d820d26e4e77295e1d21d6ce3dc1cb66b37dec830856c062cab44b42
3
+ size 278826977
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1855d283972e348fe933a3145e01585d375fcb718272ae3e950ce96eb23b507
3
+ size 1112422168
pytorch/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "dtype": "float32",
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "Business Development & Strategic Sales",
15
+ "1": "Field Sales & Outside Sales",
16
+ "2": "Inside Sales & Telesales",
17
+ "3": "Key Account & Account Management",
18
+ "4": "Retail & Store Sales",
19
+ "5": "Sales Management & Leadership",
20
+ "6": "Sales Operations & Support",
21
+ "7": "Technical Sales & Sales Engineering"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "Business Development & Strategic Sales": 0,
27
+ "Field Sales & Outside Sales": 1,
28
+ "Inside Sales & Telesales": 2,
29
+ "Key Account & Account Management": 3,
30
+ "Retail & Store Sales": 4,
31
+ "Sales Management & Leadership": 5,
32
+ "Sales Operations & Support": 6,
33
+ "Technical Sales & Sales Engineering": 7
34
+ },
35
+ "layer_norm_eps": 1e-05,
36
+ "max_position_embeddings": 514,
37
+ "model_type": "xlm-roberta",
38
+ "num_attention_heads": 12,
39
+ "num_hidden_layers": 12,
40
+ "output_past": true,
41
+ "pad_token_id": 1,
42
+ "position_embedding_type": "absolute",
43
+ "transformers_version": "4.57.6",
44
+ "type_vocab_size": 1,
45
+ "use_cache": true,
46
+ "vocab_size": 250002
47
+ }
pytorch/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4be3cea70a0db636762023d0a6dfebb84f7e71b0ca62e09e38a14d32988045e
3
+ size 1112223464
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
test_metrics.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "accuracy": 0.9264573991031391,
3
+ "f1_macro": 0.8794732273709837,
4
+ "f1_weighted": 0.9271627726484795
5
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
3
+ size 17082832
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
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": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 512,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }