Werea-TR-Topic: Turkish konu sınıflandırma

README.md

@@ -0,0 +1,19 @@
+---
+language: [tr]
+license: mit
+pipeline_tag: text-classification
+base_model: dbmdz/bert-base-turkish-cased
+tags: [turkish, text-classification, werea]
+datasets: [GoktugD/turkish-topic-classification-1.5m]
+---
+# Werea-TR-Topic — Türkçe konu sınıflandırma
+[dbmdz/bert-base-turkish-cased](https://huggingface.co/dbmdz/bert-base-turkish-cased) tabanının Türkçe konu sınıflandırma için fine-tune'u.
+20 sınıf. Doğrulama: **accuracy 100.0%**, macro-F1 100.0%.
+> Not: Sentetik ([GoktugD/turkish-topic-classification-1.5m](https://huggingface.co/datasets/GoktugD/turkish-topic-classification-1.5m)) veriyle eğitildi; gerçek-dünya kullanımında doğrulama önerilir.
+## Kullanım
+```python
+from transformers import pipeline
+clf = pipeline("text-classification", model="Werea-co/Werea-TR-Topic")
+print(clf("Örnek Türkçe metin"))
+```
+💜 [werea.co](https://werea.co)

config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "dbmdz/bert-base-turkish-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "afet haz\u0131rl\u0131\u011f\u0131",
+    "1": "ak\u0131ll\u0131 tar\u0131m",
+    "2": "a\u00e7\u0131k kaynak",
+    "3": "bulut bili\u015fim",
+    "4": "dijital ar\u015fiv",
+    "5": "do\u011fa koruma",
+    "6": "e-ticaret",
+    "7": "enerji verimlili\u011fi",
+    "8": "finansal okuryazarl\u0131k",
+    "9": "geri d\u00f6n\u00fc\u015f\u00fcm",
+    "10": "g\u00fcne\u015f enerjisi",
+    "11": "k\u00fclt\u00fcrel miras",
+    "12": "lojistik",
+    "13": "mobil sa\u011fl\u0131k",
+    "14": "robotik",
+    "15": "siber g\u00fcvenlik",
+    "16": "su tasarrufu",
+    "17": "uzaktan e\u011fitim",
+    "18": "veri bilimi",
+    "19": "\u015fehir i\u00e7i ula\u015f\u0131m"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "afet haz\u0131rl\u0131\u011f\u0131": 0,
+    "ak\u0131ll\u0131 tar\u0131m": 1,
+    "a\u00e7\u0131k kaynak": 2,
+    "bulut bili\u015fim": 3,
+    "dijital ar\u015fiv": 4,
+    "do\u011fa koruma": 5,
+    "e-ticaret": 6,
+    "enerji verimlili\u011fi": 7,
+    "finansal okuryazarl\u0131k": 8,
+    "geri d\u00f6n\u00fc\u015f\u00fcm": 9,
+    "g\u00fcne\u015f enerjisi": 10,
+    "k\u00fclt\u00fcrel miras": 11,
+    "lojistik": 12,
+    "mobil sa\u011fl\u0131k": 13,
+    "robotik": 14,
+    "siber g\u00fcvenlik": 15,
+    "su tasarrufu": 16,
+    "uzaktan e\u011fitim": 17,
+    "veri bilimi": 18,
+    "\u015fehir i\u00e7i ula\u015f\u0131m": 19
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9ac4461f5b3aa912e9a5d886e026d2932c8d082a02e80c646506bf2a68cca09
+size 442554432

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}