Add model files

README.md

@@ -0,0 +1,44 @@
+---
+language: 
+- ar
+license: apache-2.0
+widget:
+ - text: 'شلونك ؟ شخبارك ؟'
+---
+# CAMeLBER-Mix POS-GLF Model
+## Model description
+**CAMeLBERT-Mix POS-GLF Model** is a Gulf Arabic POS tagging model that was built by fine-tuning the [CAMeLBERT-Mix](https://huggingface.co/CAMeL-Lab/bert-base-arabic-camelbert-mix/) model.
+For the fine-tuning, we used the [Gumar](https://camel.abudhabi.nyu.edu/annotated-gumar-corpus/) dataset .
+Our fine-tuning procedure and the hyperparameters we used can be found in our paper *"[The Interplay of Variant, Size, and Task Type in Arabic Pre-trained Language Models](https://arxiv.org/abs/2103.06678)."* Our fine-tuning code can be found [here](https://github.com/CAMeL-Lab/CAMeLBERT).
+
+## Intended uses
+You can use the CAMeLBERT-Mix POS-GLF model as part of the transformers pipeline.
+This model will also be available in [CAMeL Tools](https://github.com/CAMeL-Lab/camel_tools) soon.
+
+#### How to use
+To use the model with a transformers pipeline:
+```python
+>>> from transformers import pipeline
+>>> pos = pipeline('text-classification', model='CAMeL-Lab/bert-base-arabic-camelbert-mix-pos-glf')
+>>> text = 'شلونك ؟ شخبارك ؟'
+>>> pos(text)
+[{'entity': 'pron_interrog', 'score': 0.82657206, 'index': 1, 'word': 'شلون', 'start': 0, 'end': 4}, {'entity': 'prep', 'score': 0.9771731, 'index': 2, 'word': '##ك', 'start': 4, 'end': 5}, {'entity': 'punc', 'score': 0.9999568, 'index': 3, 'word': '؟', 'start': 6, 'end': 7}, {'entity': 'noun', 'score': 0.9977217, 'index': 4, 'word': 'ش', 'start': 8, 'end': 9}, {'entity': 'noun', 'score': 0.99993783, 'index': 5, 'word': '##خبار', 'start': 9, 'end': 13}, {'entity': 'prep', 'score': 0.5309442, 'index': 6, 'word': '##ك', 'start': 13, 'end': 14}, {'entity': 'punc', 'score': 0.9999575, 'index': 7, 'word': '؟', 'start': 15, 'end': 16}]
+```
+*Note*: to download our models, you would need `transformers>=3.5.0`. Otherwise, you could download the models 
+## Citation
+```bibtex
+@inproceedings{inoue-etal-2021-interplay,
+    title = "The Interplay of Variant, Size, and Task Type in {A}rabic Pre-trained Language Models",
+    author = "Inoue, Go  and
+      Alhafni, Bashar  and
+      Baimukan, Nurpeiis  and
+      Bouamor, Houda  and
+      Habash, Nizar",
+    booktitle = "Proceedings of the Sixth Arabic Natural Language Processing Workshop",
+    month = apr,
+    year = "2021",
+    address = "Kyiv, Ukraine (Online)",
+    publisher = "Association for Computational Linguistics",
+    abstract = "In this paper, we explore the effects of language variants, data sizes, and fine-tuning task types in Arabic pre-trained language models. To do so, we build three pre-trained language models across three variants of Arabic: Modern Standard Arabic (MSA), dialectal Arabic, and classical Arabic, in addition to a fourth language model which is pre-trained on a mix of the three. We also examine the importance of pre-training data size by building additional models that are pre-trained on a scaled-down set of the MSA variant. We compare our different models to each other, as well as to eight publicly available models by fine-tuning them on five NLP tasks spanning 12 datasets. Our results suggest that the variant proximity of pre-training data to fine-tuning data is more important than the pre-training data size. We exploit this insight in defining an optimized system selection model for the studied tasks.",
+}
+```

config.json

@@ -0,0 +1,99 @@
+{
+  "_name_or_path": "/Users/gi372/Research/bert-base-arabic-camelbert-mix-pos-glf",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "abbrev",
+    "1": "adj",
+    "2": "adj_comp",
+    "3": "adj_num",
+    "4": "adv",
+    "5": "adv_interrog",
+    "6": "adv_rel",
+    "7": "conj",
+    "8": "conj_sub",
+    "9": "digit",
+    "10": "interj",
+    "11": "latin",
+    "12": "noun",
+    "13": "noun_num",
+    "14": "noun_prop",
+    "15": "noun_quant",
+    "16": "part",
+    "17": "part_det",
+    "18": "part_focus",
+    "19": "part_fut",
+    "20": "part_interrog",
+    "21": "part_neg",
+    "22": "part_restrict",
+    "23": "part_verb",
+    "24": "part_voc",
+    "25": "prep",
+    "26": "pron",
+    "27": "pron_dem",
+    "28": "pron_exclam",
+    "29": "pron_interrog",
+    "30": "pron_rel",
+    "31": "punc",
+    "32": "verb",
+    "33": "verb_nom",
+    "34": "verb_pseudo"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "abbrev": 0,
+    "adj": 1,
+    "adj_comp": 2,
+    "adj_num": 3,
+    "adv": 4,
+    "adv_interrog": 5,
+    "adv_rel": 6,
+    "conj": 7,
+    "conj_sub": 8,
+    "digit": 9,
+    "interj": 10,
+    "latin": 11,
+    "noun": 12,
+    "noun_num": 13,
+    "noun_prop": 14,
+    "noun_quant": 15,
+    "part": 16,
+    "part_det": 17,
+    "part_focus": 18,
+    "part_fut": 19,
+    "part_interrog": 20,
+    "part_neg": 21,
+    "part_restrict": 22,
+    "part_verb": 23,
+    "part_voc": 24,
+    "prep": 25,
+    "pron": 26,
+    "pron_dem": 27,
+    "pron_exclam": 28,
+    "pron_interrog": 29,
+    "pron_rel": 30,
+    "punc": 31,
+    "verb": 32,
+    "verb_nom": 33,
+    "verb_pseudo": 34
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.11.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0b4af01e1102d1432f4352bd483da7d1718d7a6aaa3d1a64f0dbedf705418be
+size 436487601

special_tokens_map.json

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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b430e102b2205e1bca1dd72f709f32027808b01734a85620575e22c08760ce34
+size 436592640

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "special_tokens_map_file": null, "full_tokenizer_file": null}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d34d1811193cab3dea584df888f2ac8ef373797dba5467afbd0391859c060ad
+size 1355