Hugging Face's logo

Xenova
/
french-camembert-postag-model

Token Classification
Transformers.js
ONNX
camembert
Model card Files Community
1
Xenova HF staff commited on
Commit
3e248ab
·
1 Parent(s): 861205c

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. config.json +91 -0
  2. onnx/model.onnx +3 -0
  3. onnx/model_quantized.onnx +3 -0
  4. quantize_config.json +36 -0
  5. sentencepiece.bpe.model +3 -0
  6. special_tokens_map.json +13 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +24 -0
config.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gilf/french-camembert-postag-model",
3
+ "architectures": [
4
+ "CamembertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 5,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 6,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "ADJ",
16
+ "2": "ADJWH",
17
+ "3": "ADV",
18
+ "4": "ADVWH",
19
+ "5": "CC",
20
+ "6": "CLO",
21
+ "7": "CLR",
22
+ "8": "CLS",
23
+ "9": "CS",
24
+ "10": "DET",
25
+ "11": "DETWH",
26
+ "12": "ET",
27
+ "13": "I",
28
+ "14": "NC",
29
+ "15": "NPP",
30
+ "16": "P",
31
+ "17": "P+D",
32
+ "18": "PONCT",
33
+ "19": "PREF",
34
+ "20": "PRO",
35
+ "21": "PROREL",
36
+ "22": "PROWH",
37
+ "23": "U",
38
+ "24": "V",
39
+ "25": "VIMP",
40
+ "26": "VINF",
41
+ "27": "VPP",
42
+ "28": "VPR",
43
+ "29": "VS"
44
+ },
45
+ "initializer_range": 0.02,
46
+ "intermediate_size": 3072,
47
+ "label2id": {
48
+ "ADJ": 1,
49
+ "ADJWH": 2,
50
+ "ADV": 3,
51
+ "ADVWH": 4,
52
+ "CC": 5,
53
+ "CLO": 6,
54
+ "CLR": 7,
55
+ "CLS": 8,
56
+ "CS": 9,
57
+ "DET": 10,
58
+ "DETWH": 11,
59
+ "ET": 12,
60
+ "I": 13,
61
+ "NC": 14,
62
+ "NPP": 15,
63
+ "O": 0,
64
+ "P": 16,
65
+ "P+D": 17,
66
+ "PONCT": 18,
67
+ "PREF": 19,
68
+ "PRO": 20,
69
+ "PROREL": 21,
70
+ "PROWH": 22,
71
+ "U": 23,
72
+ "V": 24,
73
+ "VIMP": 25,
74
+ "VINF": 26,
75
+ "VPP": 27,
76
+ "VPR": 28,
77
+ "VS": 29
78
+ },
79
+ "layer_norm_eps": 1e-05,
80
+ "max_position_embeddings": 514,
81
+ "model_type": "camembert",
82
+ "num_attention_heads": 12,
83
+ "num_hidden_layers": 12,
84
+ "output_past": true,
85
+ "pad_token_id": 1,
86
+ "position_embedding_type": "absolute",
87
+ "transformers_version": "4.34.0.dev0",
88
+ "type_vocab_size": 1,
89
+ "use_cache": true,
90
+ "vocab_size": 32005
91
+ }
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcedfa324f0ede94b719e60f287241522b118d34d14170e44b97a62b576501d4
3
+ size 440499080
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd69e98d99b238500f56dd711744b89c5a251a247a610c70488358a3d3600cb3
3
+ size 111303562
quantize_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "model": {
6
+ "op_types": [
7
+ "Erf",
8
+ "Where",
9
+ "Div",
10
+ "ConstantOfShape",
11
+ "Transpose",
12
+ "Mul",
13
+ "CumSum",
14
+ "Add",
15
+ "Constant",
16
+ "Sqrt",
17
+ "MatMul",
18
+ "Shape",
19
+ "Not",
20
+ "Concat",
21
+ "Equal",
22
+ "Slice",
23
+ "Expand",
24
+ "Pow",
25
+ "ReduceMean",
26
+ "Gather",
27
+ "Unsqueeze",
28
+ "Sub",
29
+ "Cast",
30
+ "Softmax",
31
+ "Reshape"
32
+ ],
33
+ "weight_type": "QInt8"
34
+ }
35
+ }
36
+ }
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
3
+ size 810912
special_tokens_map.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "cls_token": "<s>",
8
+ "eos_token": "</s>",
9
+ "mask_token": "<mask>",
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "unk_token": "<unk>"
13
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "clean_up_tokenization_spaces": true,
8
+ "cls_token": "<s>",
9
+ "eos_token": "</s>",
10
+ "mask_token": {
11
+ "__type": "AddedToken",
12
+ "content": "<mask>",
13
+ "lstrip": true,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "model_max_length": 1000000000000000019884624838656,
19
+ "pad_token": "<pad>",
20
+ "sep_token": "</s>",
21
+ "sp_model_kwargs": {},
22
+ "tokenizer_class": "CamembertTokenizer",
23
+ "unk_token": "<unk>"
24
+ }