Upload folder using huggingface_hub

__init__.py

@@ -0,0 +1,2 @@
+# Model module
+

config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "negative",
+    "1": "neutral",
+    "2": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "neutral": 1,
+    "positive": 2
+  },
+  "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",
+  "transformers_version": "4.57.0",
+  "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 sha256:905110c097ddeeda0a8b5136f91e5f8e2a2278cd9765e9eaa38feda658649203
+size 442502140

model_card.md

@@ -0,0 +1,128 @@
+---
+language: tr
+tags:
+- sentiment-analysis
+- turkish
+- bert
+- text-classification
+license: apache-2.0
+datasets:
+- winvoker/turkish-sentiment-analysis-dataset
+- WhiteAngelss/Turkce-Duygu-Analizi-Dataset
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+---
+
+# Turkish Sentiment Analysis Model
+
+A fine-tuned BERT model for Turkish sentiment analysis, trained on a combined dataset of 439,384 labeled Turkish sentences.
+
+## Model Details
+
+- **Base Model:** `dbmdz/bert-base-turkish-cased`
+- **Task:** Text Classification (Sentiment Analysis)
+- **Language:** Turkish
+- **Labels:** positive, negative, neutral
+
+## Training Data
+
+The model was trained on a combination of two high-quality Turkish sentiment datasets:
+- `winvoker/turkish-sentiment-analysis-dataset` (440,641 samples)
+- `WhiteAngelss/Turkce-Duygu-Analizi-Dataset` (440,641 samples)
+
+After deduplication and preprocessing, the final training set consisted of:
+- **Training:** 351,507 samples
+- **Validation:** 43,938 samples
+- **Test:** 43,939 samples
+
+### Label Distribution
+
+- **Positive:** 234,957 (53.5%)
+- **Neutral:** 153,809 (35.0%)
+- **Negative:** 50,618 (11.5%)
+
+## Training
+
+- **Epochs:** 3
+- **Learning Rate:** 2e-5
+- **Batch Size:** 16
+- **Max Length:** 128
+- **Optimizer:** AdamW
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+# Load model and tokenizer
+model_name = "codealchemist01/turkish-sentiment-analysis"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+# Example text
+text = "Bu ürün gerçekten harika!"
+
+# Tokenize
+inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=128)
+
+# Predict
+with torch.no_grad():
+    outputs = model(**inputs)
+    predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
+    predicted_label_id = predictions.argmax().item()
+
+# Map to label
+id2label = {0: "negative", 1: "neutral", 2: "positive"}
+predicted_label = id2label[predicted_label_id]
+confidence = predictions[0][predicted_label_id].item()
+
+print(f"Label: {predicted_label}")
+print(f"Confidence: {confidence:.4f}")
+```
+
+## Performance
+
+Evaluation metrics on the test set (43,939 samples):
+
+- **Accuracy:** 97.45%
+- **Weighted F1:** 97.42%
+- **Weighted Precision:** 97.41%
+- **Weighted Recall:** 97.45%
+
+### Per-Class Performance
+
+| Class    | Precision | Recall | F1-Score | Support |
+|----------|-----------|--------|----------|---------|
+| Negative | 91.42%    | 86.69% | 88.99%   | 5,062   |
+| Neutral  | 99.79%    | 99.96% | 99.87%   | 15,381  |
+| Positive | 97.15%    | 98.12% | 97.63%   | 23,496  |
+
+**Note:** Negative class has lower performance due to class imbalance (only 11.5% of the dataset). The model performs excellently on neutral and positive classes.
+
+## Limitations
+
+- The model may not perform well on very short texts (< 3 words)
+- Performance may vary across different domains (social media, news, reviews)
+- Class imbalance may affect performance on minority classes (negative)
+
+## Citation
+
+If you use this model, please cite:
+
+```bibtex
+@misc{turkish-sentiment-analysis,
+  title={Turkish Sentiment Analysis Model},
+  author={codealchemist01},
+  year={2024},
+  howpublished={\url{https://huggingface.co/codealchemist01/turkish-sentiment-analysis}}
+}
+```
+
+## License
+
+Apache 2.0
+

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 +1,59 @@
+{
+  "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,
+  "extra_special_tokens": {},
+  "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]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bd94595c3e7c9cafde146967d7aed03066abdb040f116da8a9c805f0161d4e7
+size 5777