commit files to HF hub
Browse files- README.md +25 -0
- config.json +25 -0
- inference.py +10 -0
- openvino_model.bin +3 -0
- openvino_model.xml +0 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
tags:
|
5 |
+
- openvino
|
6 |
+
---
|
7 |
+
|
8 |
+
# bert-base-uncased
|
9 |
+
|
10 |
+
This is the [bert-base-uncased](https://huggingface.co/bert-base-uncased) model converted to [OpenVINO](https://openvino.ai), for accellerated inference.
|
11 |
+
|
12 |
+
An example of how to do inference on this model:
|
13 |
+
```python
|
14 |
+
from optimum.intel.openvino import OVModelForMaskedLM
|
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/bert-base-uncased-ov-fp32"
|
19 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
20 |
+
model = OVModelForMaskedLM.from_pretrained(model_id)
|
21 |
+
pipe = pipeline("fill-mask", model=model, tokenizer=tokenizer)
|
22 |
+
result = pipe("I am a [MASK] model")
|
23 |
+
print(result)
|
24 |
+
```
|
25 |
+
|
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"transformers_version": "4.25.1",
|
22 |
+
"type_vocab_size": 2,
|
23 |
+
"use_cache": true,
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
inference.py
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from optimum.intel.openvino import OVModelForMaskedLM
|
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/bert-base-uncased-ov-fp32"
|
6 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
7 |
+
model = OVModelForMaskedLM.from_pretrained(model_id)
|
8 |
+
pipe = pipeline("fill-mask", model=model, tokenizer=tokenizer)
|
9 |
+
result = pipe("I am a [MASK] model")
|
10 |
+
print(result)
|
openvino_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4123ae521320c97e86c387e137d8522b4f614824c1f12fe8678bebfd9d365c31
|
3 |
+
size 531825020
|
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 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_lower_case": true,
|
4 |
+
"mask_token": "[MASK]",
|
5 |
+
"model_max_length": 512,
|
6 |
+
"name_or_path": "bert-base-uncased",
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"special_tokens_map_file": null,
|
10 |
+
"strip_accents": null,
|
11 |
+
"tokenize_chinese_chars": true,
|
12 |
+
"tokenizer_class": "BertTokenizer",
|
13 |
+
"unk_token": "[UNK]"
|
14 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|