Hugging Face's logo

Xenova
/
xlm-mlm-xnli15-1024

Fill-Mask
Transformers.js
ONNX
xlm
Model card Files Community
Xenova HF staff commited on
Commit
b593ed1
•
1 Parent(s): 144e65a

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. config.json +79 -0
  2. generation_config.json +6 -0
  3. merges.txt +0 -0
  4. onnx/model.onnx +3 -0
  5. onnx/model_quantized.onnx +3 -0
  6. quantize_config.json +33 -0
  7. special_tokens_map.json +20 -0
  8. tokenizer_config.json +58 -0
  9. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-mlm-xnli15-1024",
3
+ "architectures": [
4
+ "XLMWithLMHeadModel"
5
+ ],
6
+ "asm": false,
7
+ "attention_dropout": 0.1,
8
+ "bos_index": 0,
9
+ "bos_token_id": 0,
10
+ "causal": false,
11
+ "dropout": 0.1,
12
+ "emb_dim": 1024,
13
+ "embed_init_std": 0.02209708691207961,
14
+ "end_n_top": 5,
15
+ "eos_index": 1,
16
+ "gelu_activation": true,
17
+ "id2lang": {
18
+ "0": "ar",
19
+ "1": "bg",
20
+ "10": "th",
21
+ "11": "tr",
22
+ "12": "ur",
23
+ "13": "vi",
24
+ "14": "zh",
25
+ "2": "de",
26
+ "3": "el",
27
+ "4": "en",
28
+ "5": "es",
29
+ "6": "fr",
30
+ "7": "hi",
31
+ "8": "ru",
32
+ "9": "sw"
33
+ },
34
+ "init_std": 0.02,
35
+ "is_encoder": true,
36
+ "lang2id": {
37
+ "ar": 0,
38
+ "bg": 1,
39
+ "de": 2,
40
+ "el": 3,
41
+ "en": 4,
42
+ "es": 5,
43
+ "fr": 6,
44
+ "hi": 7,
45
+ "ru": 8,
46
+ "sw": 9,
47
+ "th": 10,
48
+ "tr": 11,
49
+ "ur": 12,
50
+ "vi": 13,
51
+ "zh": 14
52
+ },
53
+ "lang_id": 0,
54
+ "layer_norm_eps": 1e-12,
55
+ "mask_index": 5,
56
+ "mask_token_id": 0,
57
+ "max_position_embeddings": 512,
58
+ "max_vocab": 95000,
59
+ "min_count": 0,
60
+ "model_type": "xlm",
61
+ "n_heads": 8,
62
+ "n_langs": 15,
63
+ "n_layers": 12,
64
+ "pad_index": 2,
65
+ "pad_token_id": 2,
66
+ "same_enc_dec": true,
67
+ "share_inout_emb": true,
68
+ "sinusoidal_embeddings": false,
69
+ "start_n_top": 5,
70
+ "summary_activation": null,
71
+ "summary_first_dropout": 0.1,
72
+ "summary_proj_to_labels": true,
73
+ "summary_type": "first",
74
+ "summary_use_proj": true,
75
+ "transformers_version": "4.34.0.dev0",
76
+ "unk_index": 3,
77
+ "use_lang_emb": true,
78
+ "vocab_size": 95000
79
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "pad_token_id": 2,
5
+ "transformers_version": "4.34.0.dev0"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34867c2973c762f8e6890f8ffca3f10a4b0ac9965bb9d81a1ce2fc71499e197f
3
+ size 996420769
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afc4b0ea160b4ee5da5ad60c8c8dc7022450f370afd2a6a3555951b13759bc16
3
+ size 250717716
quantize_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "model": {
6
+ "op_types": [
7
+ "Shape",
8
+ "MatMul",
9
+ "Gather",
10
+ "Cast",
11
+ "Where",
12
+ "Mul",
13
+ "Pow",
14
+ "Add",
15
+ "Unsqueeze",
16
+ "Expand",
17
+ "Erf",
18
+ "Transpose",
19
+ "Reshape",
20
+ "Sqrt",
21
+ "Sub",
22
+ "Slice",
23
+ "ReduceMean",
24
+ "Constant",
25
+ "Div",
26
+ "Equal",
27
+ "Softmax",
28
+ "Concat"
29
+ ],
30
+ "weight_type": "QInt8"
31
+ }
32
+ }
33
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<special0>",
4
+ "<special1>",
5
+ "<special2>",
6
+ "<special3>",
7
+ "<special4>",
8
+ "<special5>",
9
+ "<special6>",
10
+ "<special7>",
11
+ "<special8>",
12
+ "<special9>"
13
+ ],
14
+ "bos_token": "<s>",
15
+ "cls_token": "</s>",
16
+ "mask_token": "<special1>",
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "unk_token": "<unk>"
20
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<special0>",
4
+ "<special1>",
5
+ "<special2>",
6
+ "<special3>",
7
+ "<special4>",
8
+ "<special5>",
9
+ "<special6>",
10
+ "<special7>",
11
+ "<special8>",
12
+ "<special9>"
13
+ ],
14
+ "bos_token": "<s>",
15
+ "clean_up_tokenization_spaces": true,
16
+ "cls_token": "</s>",
17
+ "do_lowercase_and_remove_accent": true,
18
+ "id2lang": {
19
+ "0": "ar",
20
+ "1": "bg",
21
+ "10": "th",
22
+ "11": "tr",
23
+ "12": "ur",
24
+ "13": "vi",
25
+ "14": "zh",
26
+ "2": "de",
27
+ "3": "el",
28
+ "4": "en",
29
+ "5": "es",
30
+ "6": "fr",
31
+ "7": "hi",
32
+ "8": "ru",
33
+ "9": "sw"
34
+ },
35
+ "lang2id": {
36
+ "ar": 0,
37
+ "bg": 1,
38
+ "de": 2,
39
+ "el": 3,
40
+ "en": 4,
41
+ "es": 5,
42
+ "fr": 6,
43
+ "hi": 7,
44
+ "ru": 8,
45
+ "sw": 9,
46
+ "th": 10,
47
+ "tr": 11,
48
+ "ur": 12,
49
+ "vi": 13,
50
+ "zh": 14
51
+ },
52
+ "mask_token": "<special1>",
53
+ "model_max_length": 512,
54
+ "pad_token": "<pad>",
55
+ "sep_token": "</s>",
56
+ "tokenizer_class": "XLMTokenizer",
57
+ "unk_token": "<unk>"
58
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff