commit files to HF hub

README.md

@@ -0,0 +1,25 @@
+---
+language:
+- en
+tags:
+- openvino
+---
+
+# bert-large-cased-whole-word-masking-finetuned-squad
+
+This is the [bert-large-cased-whole-word-masking-finetuned-squad](https://huggingface.co/bert-large-cased-whole-word-masking-finetuned-squad) model converted to [OpenVINO](https://openvino.ai), for accellerated inference.
+
+An example of how to do inference on this model:
+```python
+from optimum.intel.openvino import OVModelForQuestionAnswering
+from transformers import AutoTokenizer, pipeline
+
+# model_id should be set to either a local directory or a model available on the HuggingFace hub.
+model_id = "helenai/bert-large-cased-whole-word-masking-finetuned-squad-ov"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = OVModelForQuestionAnswering.from_pretrained(model_id)
+pipe = pipeline("question-answering", model=model, tokenizer=tokenizer)
+result = pipe("What is OpenVINO?", "OpenVINO is a framework that accelerates deep learning inferencing")
+print(result)
+```
+

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "bert-large-cased-whole-word-masking-finetuned-squad",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.27.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

inference.py

@@ -0,0 +1,10 @@
+from optimum.intel.openvino import OVModelForQuestionAnswering
+from transformers import AutoTokenizer, pipeline
+
+# model_id should be set to either a local directory or a model available on the HuggingFace hub.
+model_id = "helenai/bert-large-cased-whole-word-masking-finetuned-squad-ov"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = OVModelForQuestionAnswering.from_pretrained(model_id)
+pipe = pipeline("question-answering", model=model, tokenizer=tokenizer)
+result = pipe("What is OpenVINO?", "OpenVINO is a framework that accelerates deep learning inferencing")
+print(result)

openvino_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80bce85eaafa15a907e7c7c5b00f2947201d0d207001380eeac10bc9953fff2c
+size 1330131116

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}