Add model files

README.md

@@ -0,0 +1,45 @@
+---
+language: 
+- ar
+license: apache-2.0
+widget:
+ - text: "عامل ايه ؟"
+---
+# CAMeLBERT-Mix DID Corpus26 Model
+## Model description
+**CAMeLBERT-Mix DID Corpus26 Model** is a dialect identification (DID) 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 [MADAR Corpus 26](https://camel.abudhabi.nyu.edu/madar-shared-task-2019/) dataset, which includes 26 labels.
+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 DID Corpus26 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
+>>> did = pipeline('text-classification', model='CAMeL-Lab/bert-base-arabic-camelbert-mix-did-madar26')
+>>> sentences = ['عامل ايه ؟', 'شلونك ؟ شخبارك ؟']
+>>> did(sentences)
+[{'label': 'CAI', 'score': 0.8751305937767029},
+ {'label': 'DOH', 'score': 0.9867215156555176}]
+```
+*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 +1,78 @@
+{
+  "_name_or_path": "bert-base-arabic-camelbert-mix-did-madar26/",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "arabic_did",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "KHA",
+    "1": "TUN",
+    "10": "TRI",
+    "11": "ALG",
+    "12": "MSA",
+    "13": "FES",
+    "14": "BEN",
+    "15": "SAL",
+    "16": "JER",
+    "17": "BEI",
+    "18": "SFX",
+    "19": "MUS",
+    "2": "MOS",
+    "20": "JED",
+    "21": "RIY",
+    "22": "RAB",
+    "23": "DAM",
+    "24": "ASW",
+    "25": "AMM",
+    "3": "CAI",
+    "4": "BAG",
+    "5": "ALE",
+    "6": "DOH",
+    "7": "ALX",
+    "8": "SAN",
+    "9": "BAS"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ALE": 5,
+    "ALG": 11,
+    "ALX": 7,
+    "AMM": 25,
+    "ASW": 24,
+    "BAG": 4,
+    "BAS": 9,
+    "BEI": 17,
+    "BEN": 14,
+    "CAI": 3,
+    "DAM": 23,
+    "DOH": 6,
+    "FES": 13,
+    "JED": 20,
+    "JER": 16,
+    "KHA": 0,
+    "MOS": 2,
+    "MSA": 12,
+    "MUS": 19,
+    "RAB": 22,
+    "RIY": 21,
+    "SAL": 15,
+    "SAN": 8,
+    "SFX": 18,
+    "TRI": 10,
+    "TUN": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

eval_results_test.txt

@@ -0,0 +1,4 @@
+acc = 62.86538461538461
+f1 = 62.908251684423114
+precision = 63.30140739141851
+recall = 62.86538461538461

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:664ab443c4f4bbfdf8199cc31e9efc3f3774401ebe8553e8db9b1c0ba77dabe5
+size 872870730

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13993e45dfaa873d0e5d7bae7a92fded87bf6539c9ae8c10e4575097df07985e
+size 436459917

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89a7b2895340bad6dc702f94e4d47001ebab74ee2203746d157540df4e87a0f1
+size 326

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:c8a020beaad2573febc55431d8d74fa42d6fb1bb61b3f0399d1afe3ca1611883
+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 sha256:939f5f588e71b04f86d857acccd25cc371f2b4a9903387e4b81c4e199f8f59d8
+size 1397