Upload folder using huggingface_hub

README.md

@@ -1,3 +1,39 @@
----
-license: mit
----
+
+---
+language: tr
+tags:
+- turkish
+- sentiment
+- classification
+- tensorflow
+license: mit
+---
+
+# Turkish Sentiment Analysis Model
+
+This model is a fine-tuned version of [emre/turkish-sentiment-analysis](https://huggingface.co/emre/turkish-sentiment-analysis) for sentiment analysis in Turkish.
+
+## Model description
+
+The model is based on BERT and fine-tuned on a Turkish sentiment analysis dataset. It classifies text into three sentiment categories.
+
+## Intended uses & limitations
+
+This model is intended for sentiment analysis of Turkish text. It should be used for research purposes or general sentiment analysis tasks in Turkish.
+
+## Training data
+
+The model was fine-tuned on a combined dataset of labeled Turkish sentiment data.
+
+## Training procedure
+
+The model was fine-tuned using the following hyperparameters:
+- learning rate: 2e-5
+- batch size: 16
+- epochs: 3 (with early stopping)
+- optimizer: Adam (beta1=0.9, beta2=0.999, epsilon=1e-8)
+
+## Evaluation results
+
+Test Accuracy: 0.9286
+

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "emre/turkish-sentiment-analysis",
+  "_num_labels": 3,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Negative",
+    "1": "Notr",
+    "2": "Positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Negative": 0,
+    "Notr": 1,
+    "Positive": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_length": 64,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "padding": "max_length",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 128000
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0c8fcb07d38ff37d44aba1f9a268b2e9f712e7635699c688ff3c9f10e3e74fc
+size 737678620

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "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": true,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "max_length": 64,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}