upload the first version

READMR.md

@@ -0,0 +1,58 @@
+---
+language: ar
+datasets:
+- Marefa-NER
+---
+
+# Marefa NER نموذج المعرفة لتصنيف أجزاء النص
+
+## Model description
+
+**Marefa-NER** is a Large Arabic NER model which built on completely new dataset and targets to extract up to 9 different types of entities
+```
+Person, Location, Organization, Nationality, Job, Product, Event, Time, Art-Work
+```
+
+نموذج المعرفة لتصنيف أجزاء النص. نموذج جديد كليا من حيث البيانات المستخدمة في تدريب النموذج. 
+كذلك يستهدف النموذج تصنيف حتى 9 أنواع مختلفة من أجزاء النص
+```
+شخص - مكان - منظمة - جنسية - وظيفة - منتج - حدث - توقيت - عمل إبداعي
+```
+
+## How to use كيف تستخدم النموذج
+
+Install transformers
+
+`$ pip3 install transformers==4.3.0`
+
+> If you are using `Google Colab`, please restart your runtime after installing the packages.
+
+-----------
+
+```python
+from transformers import AutoTokenizer, AutoModelForTokenClassification
+from transformers import pipeline
+
+# ===== import the model
+m_name = "marefa-nlp/marefa-ner"
+tokenizer = AutoTokenizer.from_pretrained(m_name)
+model = AutoModelForTokenClassification.from_pretrained(m_name)
+
+# ===== build the NER pipeline
+nlp = pipeline("ner", model=model, tokenizer=tokenizer, grouped_entities=True)
+
+# ===== extract the entities from a sample text
+example = 'قاد عمر المختار القوات في ليبيا ضد الجيش الإيطالي'
+ner_results = nlp(example)
+
+# ===== print the ner_results
+for ent in ner_results:
+  print(ent["word"], '->' ,ent['entity_group'], " # score:", "%.2f" % ent['score'])
+  
+#####
+# عمر المختار -> person  # score: 1.00
+# ليبيا -> location  # score: 0.99
+# الجيش الإيطالي -> organization  # score: 0.99
+####
+
+```

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "marefa-ner",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "O", "1": "B-job", "2": "I-job", "3": "B-nationality", "4": "B-person", "5": "I-person", "6": "B-location", "7": "B-time", "8": "I-time", "9": "B-event", "10": "I-event", "11": "B-organization", "12": "I-organization", "13": "I-location", "14": "I-nationality", "15": "B-product", "16": "I-product", "17": "B-artwork", "18": "I-artwork"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+      "O": 0, "B-job": 1, "I-job": 2, "B-nationality": 3, "B-person": 4, "I-person": 5, "B-location": 6, "B-time": 7, "I-time": 8, "B-event": 9, "I-event": 10, "B-organization": 11, "I-organization": 12, "I-location": 13, "I-nationality": 14, "B-product": 15, "I-product": 16, "B-artwork": 17, "I-artwork": 18
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.3.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model_args.json

@@ -0,0 +1 @@
+{"adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "adafactor_eps": [1e-30, 0.001], "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_beta1": null, "adafactor_scale_parameter": true, "adafactor_relative_step": true, "adafactor_warmup_init": true, "eval_batch_size": 8, "evaluate_during_training": false, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 2e-05, "local_rank": -1, "logging_steps": 50, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "xlm-roberta-large", "model_type": "xlmroberta", "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 10, "optimizer": "AdamW", "output_dir": "outputs/", "overwrite_output_dir": true, "process_count": 1, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_steps": 2000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "train_batch_size": 16, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_multiprocessing": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 563, "weight_decay": 0.001, "model_class": "NERModel", "classification_report": false, "labels_list": ["O", "B-job", "I-job", "B-nationality", "B-person", "I-person", "B-location", "B-time", "I-time", "B-event", "I-event", "B-organization", "I-organization", "I-location", "I-nationality", "B-product", "I-product", "B-artwork", "I-artwork"], "lazy_loading": false, "lazy_loading_start_line": 0, "onnx": false, "special_tokens_list": []}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f67e14bc3fe36510f7f3fa99726a5240dc63cbb60f051f5b6b97f4f82377b53
+size 4471121457

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcb9993a3bf8dc52862ea7ee98642de4675be90a7efccce629abc35749268364
+size 2235610244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8da0636dfe95dd35ec9c3de89e2da9babbe4b94bbb061482b1a4915cdb79c23
+size 623

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "do_lower_case": false, "model_max_length": 512, "name_or_path": "xlm-roberta-large"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8929d8bac9dae4c7101ccfe58a662b7132989582536babf570858e8bf404898
+size 3055