helenai commited on
Commit
febb7b6
1 Parent(s): 8f04d11

commit files to HF hub

Browse files
README.md ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ tags:
5
+ - openvino
6
+ ---
7
+
8
+ # echarlaix/bert-large-uncased-whole-word-masking-finetuned-sst-2
9
+
10
+ This is the [echarlaix/bert-large-uncased-whole-word-masking-finetuned-sst-2](https://huggingface.co/echarlaix/bert-large-uncased-whole-word-masking-finetuned-sst-2) model converted to [OpenVINO](https://openvino.ai), for accelerated inference.
11
+
12
+ An example of how to do inference on this model:
13
+ ```python
14
+ from optimum.intel import OVModelForSequenceClassification
15
+ from transformers import AutoTokenizer, pipeline
16
+
17
+ # model_id should be set to either a local directory or a model available on the HuggingFace hub.
18
+ model_id = "helenai/echarlaix-bert-large-uncased-whole-word-masking-finetuned-sst-2-ov"
19
+ tokenizer = AutoTokenizer.from_pretrained(model_id)
20
+ model = OVModelForSequenceClassification.from_pretrained(model_id)
21
+ pipe = pipeline("text-classification", model=model, tokenizer=tokenizer)
22
+ result = pipe("hello world")
23
+ print(result)
24
+ ```
25
+
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "echarlaix/bert-large-uncased-whole-word-masking-finetuned-sst-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "finetuning_task": "sst2",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "pad_token_id": 0,
21
+ "position_embedding_type": "absolute",
22
+ "transformers_version": "4.42.0.dev0",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
inference.py ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ from optimum.intel import OVModelForSequenceClassification
2
+ from transformers import AutoTokenizer, pipeline
3
+
4
+ # model_id should be set to either a local directory or a model available on the HuggingFace hub.
5
+ model_id = "helenai/echarlaix-bert-large-uncased-whole-word-masking-finetuned-sst-2-ov"
6
+ tokenizer = AutoTokenizer.from_pretrained(model_id)
7
+ model = OVModelForSequenceClassification.from_pretrained(model_id)
8
+ pipe = pipeline("text-classification", model=model, tokenizer=tokenizer)
9
+ result = pipe("hello world")
10
+ print(result)
openvino_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d6982d2c11ffec1bb0713d7c53238c04bc106837238772a51e161b62f6fb222
3
+ size 670292154
openvino_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff