Commit
•
3f0ece2
1
Parent(s):
11b2b5c
Adding ONNX file of this model (#9)
Browse files- Adding ONNX file of this model (029ab96f69eaef5e93658f3959175d7c769056ea)
Co-authored-by: gheis <aliaagheis@users.noreply.huggingface.co>
- .gitattributes +2 -0
- onnx/config.json +44 -0
- onnx/model.onnx +3 -0
- onnx/model.onnx_data +3 -0
- onnx/sentencepiece.bpe.model +3 -0
- onnx/special_tokens_map.json +15 -0
- onnx/tokenizer.json +3 -0
- onnx/tokenizer_config.json +22 -0
.gitattributes
CHANGED
@@ -26,3 +26,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
29 |
+
onnx/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
30 |
+
onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
|
onnx/config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "oliverguhr/fullstop-punctuation-multilang-large",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"id2label": {
|
15 |
+
"0": "0",
|
16 |
+
"1": ".",
|
17 |
+
"2": ",",
|
18 |
+
"3": "?",
|
19 |
+
"4": "-",
|
20 |
+
"5": ":"
|
21 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 4096,
|
24 |
+
"label2id": {
|
25 |
+
",": 2,
|
26 |
+
"-": 4,
|
27 |
+
".": 1,
|
28 |
+
"0": 0,
|
29 |
+
":": 5,
|
30 |
+
"?": 3
|
31 |
+
},
|
32 |
+
"layer_norm_eps": 1e-05,
|
33 |
+
"max_position_embeddings": 514,
|
34 |
+
"model_type": "xlm-roberta",
|
35 |
+
"num_attention_heads": 16,
|
36 |
+
"num_hidden_layers": 24,
|
37 |
+
"output_past": true,
|
38 |
+
"pad_token_id": 1,
|
39 |
+
"position_embedding_type": "absolute",
|
40 |
+
"transformers_version": "4.30.2",
|
41 |
+
"type_vocab_size": 1,
|
42 |
+
"use_cache": true,
|
43 |
+
"vocab_size": 250002
|
44 |
+
}
|
onnx/model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8414d4e6e5b8f586030fd0bdec34145a24a8eea7c9b7e19fb836dff73773c618
|
3 |
+
size 617774
|
onnx/model.onnx_data
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dda38a70eda9e9d0827c0a3ea3fe27e8f553deeab397c0652b722739fd4fed06
|
3 |
+
size 2235387904
|
onnx/sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
onnx/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 |
+
}
|
onnx/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de3788bb2f349135f2ad2e2b10dff3cee7f23fab906a5fbdadf20bc963b05b4c
|
3 |
+
size 17098080
|
onnx/tokenizer_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"cls_token": "<s>",
|
6 |
+
"eos_token": "</s>",
|
7 |
+
"mask_token": {
|
8 |
+
"__type": "AddedToken",
|
9 |
+
"content": "<mask>",
|
10 |
+
"lstrip": true,
|
11 |
+
"normalized": true,
|
12 |
+
"rstrip": false,
|
13 |
+
"single_word": false
|
14 |
+
},
|
15 |
+
"model_max_length": 512,
|
16 |
+
"pad_token": "<pad>",
|
17 |
+
"sep_token": "</s>",
|
18 |
+
"sp_model_kwargs": {},
|
19 |
+
"strip_accent": false,
|
20 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
21 |
+
"unk_token": "<unk>"
|
22 |
+
}
|