commit files to HF hub

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,25 @@
+---
+language:
+- en
+tags:
+- openvino
+---
+
+# papluca/xlm-roberta-base-language-detection
+
+This is the [papluca/xlm-roberta-base-language-detection](https://huggingface.co/papluca/xlm-roberta-base-language-detection) 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 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/papluca-xlm-roberta-base-language-detection-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 +1,73 @@
+{
+  "_name_or_path": "papluca/xlm-roberta-base-language-detection",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "ja",
+    "1": "nl",
+    "2": "ar",
+    "3": "pl",
+    "4": "de",
+    "5": "it",
+    "6": "pt",
+    "7": "tr",
+    "8": "es",
+    "9": "hi",
+    "10": "el",
+    "11": "ur",
+    "12": "bg",
+    "13": "en",
+    "14": "fr",
+    "15": "zh",
+    "16": "ru",
+    "17": "th",
+    "18": "sw",
+    "19": "vi"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ar": 2,
+    "bg": 12,
+    "de": 4,
+    "el": 10,
+    "en": 13,
+    "es": 8,
+    "fr": 14,
+    "hi": 9,
+    "it": 5,
+    "ja": 0,
+    "nl": 1,
+    "pl": 3,
+    "pt": 6,
+    "ru": 16,
+    "sw": 18,
+    "th": 17,
+    "tr": 7,
+    "ur": 11,
+    "vi": 19,
+    "zh": 15
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

inference.py

@@ -0,0 +1,10 @@
+from optimum.intel.openvino 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/papluca-xlm-roberta-base-language-detection-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 sha256:76a8eca0cd1b62d3acb85a85b31adf8feede9d3c791d3a84f2fc49f7f4cc274b
+size 556122384

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
+size 17082660

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "papluca/xlm-roberta-base-language-detection",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}