commit files to HF hub

README.md

@@ -0,0 +1,25 @@
+---
+language:
+- en
+tags:
+- openvino
+---
+
+# echarlaix/bert-large-uncased-whole-word-masking-finetuned-sst-2
+
+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.
+
+An example of how to do inference on this model:
+```python
+from optimum.intel import OVModelForSequenceClassification
+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/echarlaix-bert-large-uncased-whole-word-masking-finetuned-sst-2-ov"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = OVModelForSequenceClassification.from_pretrained(model_id)
+pipe = pipeline("text-classification", model=model, tokenizer=tokenizer)
+result = pipe("hello world")
+print(result)
+```
+

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "echarlaix/bert-large-uncased-whole-word-masking-finetuned-sst-2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "sst2",
+  "gradient_checkpointing": false,
+  "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,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.42.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

inference.py

@@ -0,0 +1,10 @@
+from optimum.intel import OVModelForSequenceClassification
+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/echarlaix-bert-large-uncased-whole-word-masking-finetuned-sst-2-ov"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = OVModelForSequenceClassification.from_pretrained(model_id)
+pipe = pipeline("text-classification", model=model, tokenizer=tokenizer)
+result = pipe("hello world")
+print(result)

openvino_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d6982d2c11ffec1bb0713d7c53238c04bc106837238772a51e161b62f6fb222
+size 670292154

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 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}