Add distilbert SST2 NNCF model

README.md

@@ -0,0 +1,38 @@
+---
+language: en
+license: apache-2.0
+datasets:
+- sst2
+- glue
+tags:
+- openvino
+---
+
+## distilbert-base-uncased-finetuned-sst-2-english
+
+[distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english) quantized with NNCF PTQ and exported to the OpenVINO IR.
+
+**Model Description:** l is This model reaches an accuracy of 90.0 on the validation set. See [ov\_config.json](./ov_config.json) for the quantization config.
+
+## Usage example
+
+You can use this model with Transformers *pipeline*.
+
+```python
+from transformers import AutoTokenizer, pipeline
+from optimum.intel.openvino import OVModelForSequenceClassification
+
+model_id = "helenai/distilbert-base-uncased-finetuned-sst-2-english-ov-int8"
+model = OVModelForSequenceClassification.from_pretrained(model_id)
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+cls_pipe = pipeline("text-classification", model=model, tokenizer=tokenizer)
+text = "He's a dreadful magician."
+outputs = cls_pipe(text)
+print(outputs)
+```
+
+Example output:
+
+```bash
+[{'label': 'NEGATIVE', 'score': 0.9929909706115723}]
+```

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "sst-2",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.22.2",
+  "vocab_size": 30522
+}

ov_config.json

@@ -0,0 +1,49 @@
+{
+  "_commit_hash": null,
+  "compression": {
+    "algorithm": "quantization",
+    "ignored_scopes": [
+      "{re}.*Embeddings.*",
+      "{re}.*__add___[0-1]",
+      "{re}.*layer_norm_0",
+      "{re}.*matmul_1",
+      "{re}.*__truediv__*"
+    ],
+    "initializer": {
+      "batchnorm_adaptation": {
+        "num_bn_adaptation_samples": 0
+      },
+      "range": {
+        "num_init_samples": 300,
+        "type": "mean_min_max"
+      }
+    },
+    "overflow_fix": "disable",
+    "preset": "mixed",
+    "scope_overrides": {
+      "activations": {
+        "{re}.*matmul_0": {
+          "mode": "symmetric"
+        }
+      }
+    }
+  },
+  "input_info": [
+    {
+      "sample_size": [
+        8,
+        256
+      ],
+      "type": "long"
+    },
+    {
+      "sample_size": [
+        8,
+        256
+      ],
+      "type": "long"
+    }
+  ],
+  "optimum_version": "1.4.0",
+  "transformers_version": "4.22.2"
+}

ov_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5051f5e3c6a1c8cd9f51755c8691299c9938daa2ef94def5b709950c630677c
+size 138817460

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 +1,16 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}