Duplicate from TTimur/xlm-roberta-base-kyrgyzNER

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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 +1,178 @@
+---
+license: mit
+base_model: xlm-roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: xlm-roberta-base-kyrgyzNER
+  results: []
+language:
+- ky
+---
+
+
+
+# kyrgyzNER model (xlm-roberta-base) by The_Cramer_Project
+
+
+- The original repository: https://github.com/Akyl-AI/KyrgyzNER
+- Paper will be uploaded soon
+- KyrgyzNER dataset and Codes will be uploaded soon
+
+
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the KyrgyzNER dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3273
+- Precision: 0.7090
+- Recall: 0.6946
+- F1: 0.7017
+- Accuracy: 0.9119
+
+
+## How to use
+You can use this model with the Transformers pipeline for NER. 
+
+```python
+from transformers import AutoTokenizer, AutoModelForTokenClassification, AutoConfig
+from transformers import pipeline
+
+id2label = {
+'LABEL_0': 'B-NATIONAL',
+ 'LABEL_1': 'I-PLANT',
+ 'LABEL_2': 'I-ORGANISATION',
+ 'LABEL_3': 'B-ORGANISATION',
+ 'LABEL_4': 'B-MEDIA',
+ 'LABEL_5': 'I-ARTIFACT',
+ 'LABEL_6': 'B-AWARD',
+ 'LABEL_7': 'B-UNKNOWN',
+ 'LABEL_8': 'I-LOCATION',
+ 'LABEL_9': 'B-PERSON',
+ 'LABEL_10': 'I-LEGAL',
+ 'LABEL_11': 'B-BUSINESS',
+ 'LABEL_12': 'B-ACRONYM',
+ 'LABEL_13': 'I-PERIOD',
+ 'LABEL_14': 'B-INSTITUTION',
+ 'LABEL_15': 'I-MEASURE',
+ 'LABEL_16': 'B-CREATION',
+ 'LABEL_17': 'I-ACRONYM',
+ 'LABEL_18': 'I-AWARD',
+ 'LABEL_19': 'I-WEBSITE',
+ 'LABEL_20': 'B-PERIOD',
+ 'LABEL_21': 'I-PERSON',
+ 'LABEL_22': 'I-PERSON_TYPE',
+ 'LABEL_23': 'B-SUBSTANCE',
+ 'LABEL_24': 'O',
+ 'LABEL_25': 'B-PLANT',
+ 'LABEL_26': 'I-INSTITUTION',
+ 'LABEL_27': 'I-SUBSTANCE',
+ 'LABEL_28': 'I-INSTALLATION',
+ 'LABEL_29': 'B-CONCEPT',
+ 'LABEL_30': 'B-TITLE',
+ 'LABEL_31': 'I-EVENT',
+ 'LABEL_32': 'B-ARTIFACT',
+ 'LABEL_33': 'B-MEASURE',
+ 'LABEL_34': 'B-LOCATION',
+ 'LABEL_35': 'I-BUSINESS',
+ 'LABEL_36': 'B-ANIMAL',
+ 'LABEL_37': 'B-PERSON_TYPE',
+ 'LABEL_38': 'B-INSTALLATION',
+ 'LABEL_39': 'I-TITLE',
+ 'LABEL_40': 'B-IDENTIFIER',
+ 'LABEL_41': 'I-IDENTIFIER',
+ 'LABEL_42': 'B-LEGAL',
+ 'LABEL_43': 'I-MEDIA',
+ 'LABEL_44': 'I-CONCEPT',
+ 'LABEL_45': 'I-UNKNOWN',
+ 'LABEL_46': 'B-EVENT',
+ 'LABEL_47': 'B-WEBSITE',
+ 'LABEL_48': 'I-NATIONAL',
+ 'LABEL_49': 'I-CREATION',
+ 'LABEL_50': 'I-ANIMAL'}
+
+model_ckpt = "TTimur/xlm-roberta-base-kyrgyzNER"
+
+config = AutoConfig.from_pretrained(model_ckpt)
+tokenizer = AutoTokenizer.from_pretrained(model_ckpt)
+model = AutoModelForTokenClassification.from_pretrained(model_ckpt, config = config)
+
+# aggregation_strategy = "none"
+nlp = pipeline("ner", model = model, tokenizer = tokenizer, aggregation_strategy = "none")
+
+example = "Кыргызстан Орто Азиянын түндүк-чыгышында орун алган мамлекет."
+ner_results = nlp(example)
+for result in ner_results:
+    result.update({'entity': id2label[result['entity']]})
+    print(result)
+    
+# output:
+# {'entity': 'B-LOCATION', 'score': 0.95103735, 'index': 1, 'word': '▁Кыргызстан', 'start': 0, 'end': 10}
+# {'entity': 'B-LOCATION', 'score': 0.79447913, 'index': 2, 'word': '▁Ор', 'start': 11, 'end': 13}
+# {'entity': 'I-LOCATION', 'score': 0.8703734, 'index': 3, 'word': 'то', 'start': 13, 'end': 15}
+# {'entity': 'I-LOCATION', 'score': 0.942387, 'index': 4, 'word': '▁Азия', 'start': 16, 'end': 20}
+# {'entity': 'I-LOCATION', 'score': 0.8542615, 'index': 5, 'word': 'нын', 'start': 20, 'end': 23}
+# {'entity': 'I-LOCATION', 'score': 0.70930535, 'index': 6, 'word': '▁түн', 'start': 24, 'end': 27}
+# {'entity': 'I-LOCATION', 'score': 0.6540094, 'index': 7, 'word': 'дүк', 'start': 27, 'end': 30}
+# {'entity': 'I-LOCATION', 'score': 0.63446337, 'index': 8, 'word': '-', 'start': 30, 'end': 31}
+# {'entity': 'I-LOCATION', 'score': 0.6204858, 'index': 9, 'word': 'чы', 'start': 31, 'end': 33}
+# {'entity': 'I-LOCATION', 'score': 0.6786872, 'index': 10, 'word': 'г', 'start': 33, 'end': 34}
+# {'entity': 'I-LOCATION', 'score': 0.64190257, 'index': 11, 'word': 'ыш', 'start': 34, 'end': 36}
+# {'entity': 'O', 'score': 0.64438057, 'index': 12, 'word': 'ында', 'start': 36, 'end': 40}
+# {'entity': 'O', 'score': 0.9916931, 'index': 13, 'word': '▁орун', 'start': 41, 'end': 45}
+# {'entity': 'O', 'score': 0.9953047, 'index': 14, 'word': '▁алган', 'start': 46, 'end': 51}
+# {'entity': 'O', 'score': 0.9901377, 'index': 15, 'word': '▁мамлекет', 'start': 52, 'end': 60}
+# {'entity': 'O', 'score': 0.99605453, 'index': 16, 'word': '.', 'start': 60, 'end': 61}
+
+
+token = ""
+label_list = []
+token_list = []
+
+for result in ner_results:
+    if result["word"].startswith("▁"):
+        if token:
+            token_list.append(token.replace("▁", ""))
+        token = result["word"]
+        label_list.append(result["entity"])
+    else:
+        token += result["word"]
+
+token_list.append(token.replace("▁", ""))
+
+for token, label in zip(token_list, label_list):
+    print(f"{token}\t{label}")
+
+
+# output:
+# Кыргызстан    B-LOCATION
+# Орто  B-LOCATION
+# Азиянын   I-LOCATION
+# түндүк-чыгышында  I-LOCATION
+# орун  O
+# алган O
+# мамлекет. O
+
+# aggregation_strategy = "simple"
+nlp = pipeline("ner", model = model, tokenizer = tokenizer, aggregation_strategy = "simple")
+example = "Кыргызстан Орто Азиянын түндүк-чыгышында орун алган мамлекет."
+
+ner_results = nlp(example)
+for result in ner_results:
+    result.update({'entity_group': id2label[result['entity_group']]})
+    print(result)
+
+# output:
+# {'entity_group': 'B-LOCATION', 'score': 0.87275827, 'word': 'Кыргызстан Ор', 'start': 0, 'end': 13}
+# {'entity_group': 'I-LOCATION', 'score': 0.73398614, 'word': 'то Азиянын түндүк-чыгыш', 'start': 13, 'end': 36}
+# {'entity_group': 'O', 'score': 0.92351407, 'word': 'ында орун алган мамлекет.', 'start': 36, 'end': 61}
+
+```
+
+
+# NE classes
+
+**PERSON**, **LOCATION** , **MEASURE** , **INSTITUTION** , **PERIOD** , **ORGANISATION** , **MEDIA** , **TITLE** , **BUSINESS** , **LEGAL** , **EVENT** , **ARTIFACT** , **INSTALLATION** , **PERSON_TYPE**, **NATIONAL**, **CONCEPT**, **CREATION**, **WEBSITE**, **SUBSTANCE**, **ACRONYM**, **IDENTIFIER**, **UNKNOWN**, **AWARD**, **ANIMAL**

config.json

@@ -0,0 +1,134 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "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": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27",
+    "28": "LABEL_28",
+    "29": "LABEL_29",
+    "30": "LABEL_30",
+    "31": "LABEL_31",
+    "32": "LABEL_32",
+    "33": "LABEL_33",
+    "34": "LABEL_34",
+    "35": "LABEL_35",
+    "36": "LABEL_36",
+    "37": "LABEL_37",
+    "38": "LABEL_38",
+    "39": "LABEL_39",
+    "40": "LABEL_40",
+    "41": "LABEL_41",
+    "42": "LABEL_42",
+    "43": "LABEL_43",
+    "44": "LABEL_44",
+    "45": "LABEL_45",
+    "46": "LABEL_46",
+    "47": "LABEL_47",
+    "48": "LABEL_48",
+    "49": "LABEL_49",
+    "50": "LABEL_50"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_28": 28,
+    "LABEL_29": 29,
+    "LABEL_3": 3,
+    "LABEL_30": 30,
+    "LABEL_31": 31,
+    "LABEL_32": 32,
+    "LABEL_33": 33,
+    "LABEL_34": 34,
+    "LABEL_35": 35,
+    "LABEL_36": 36,
+    "LABEL_37": 37,
+    "LABEL_38": 38,
+    "LABEL_39": 39,
+    "LABEL_4": 4,
+    "LABEL_40": 40,
+    "LABEL_41": 41,
+    "LABEL_42": 42,
+    "LABEL_43": 43,
+    "LABEL_44": 44,
+    "LABEL_45": 45,
+    "LABEL_46": 46,
+    "LABEL_47": 47,
+    "LABEL_48": 48,
+    "LABEL_49": 49,
+    "LABEL_5": 5,
+    "LABEL_50": 50,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:825a899432c24c62b1430f2bad2c3a5b37a76ccc4e9eaf7ab818300be4bd6a98
+size 1109993156

runs/Feb17_18-51-14_24317775ef61/events.out.tfevents.1708195877.24317775ef61.13761.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:030612b965576e2e38ad236ffd59c8729c1f478f220d857416a6956891bbd7d5
+size 11640

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 sha256:9a4661b2cb6b8a1007906509fe18cbfbc03062a086102bf7b80cfedb80f16c37
+size 17082854

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e9e1d454a8e2cdffcb175d293b4fbf7ed3b7ee03c3cea766485fa493c950f84
+size 4600