Upload folder using huggingface_hub

README.md

@@ -11,11 +11,11 @@ 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.
+This model is a fine-tuned version of [VRLLab/TurkishBERTweet](https://huggingface.co/VRLLab/TurkishBERTweet) 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.
+The model is based on BERT and fine-tuned on a Turkish sentiment analysis dataset. It classifies text into three sentiment categories. Negative, Pozitive and Notr.
 
 ## Intended uses & limitations
 
@@ -28,12 +28,12 @@ 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)
+- learning rate: 1e-5
+- batch size: 8
+- epochs: 2 (with early stopping)
 - optimizer: Adam (beta1=0.9, beta2=0.999, epsilon=1e-8)
 
 ## Evaluation results
 
-Test Accuracy: 0.9286
+Test Accuracy: 0.9433
 

config.json

@@ -1,39 +1,36 @@
 {
-  "_name_or_path": "emre/turkish-sentiment-analysis",
-  "_num_labels": 3,
+  "_name_or_path": "VRLLab/TurkishBERTweet",
   "architectures": [
-    "BertForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
   "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": "Negative",
-    "1": "Notr",
-    "2": "Positive"
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "Negative": 0,
-    "Notr": 1,
-    "Positive": 2
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
   },
-  "layer_norm_eps": 1e-12,
-  "max_length": 64,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 0,
-  "padding": "max_length",
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
-  "problem_type": "single_label_classification",
-  "torch_dtype": "float32",
   "transformers_version": "4.42.4",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 128000
+  "vocab_size": 100000
 }

special_tokens_map.json

@@ -1,34 +1,48 @@
 {
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "cls_token": {
-    "content": "[CLS]",
+    "content": "<s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "mask_token": {
-    "content": "[MASK]",
+  "eos_token": {
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "pad_token": {
-    "content": "[PAD]",
+    "content": "<pad>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "sep_token": {
-    "content": "[SEP]",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
-    "content": "[UNK]",
+    "content": "<unk>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0c8fcb07d38ff37d44aba1f9a268b2e9f712e7635699c688ff3c9f10e3e74fc
-size 737678620
+oid sha256:aa8ebff93bbb79388cda21d679f467214734cb5ad36023cf3c447f5b1125db2a
+size 651667264

tokenizer_config.json

@@ -1,7 +1,8 @@
 {
+  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +10,7 @@
       "special": true
     },
     "1": {
-      "content": "[UNK]",
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +18,7 @@
       "special": true
     },
     "2": {
-      "content": "[CLS]",
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -25,7 +26,7 @@
       "special": true
     },
     "3": {
-      "content": "[SEP]",
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -33,7 +34,87 @@
       "special": true
     },
     "4": {
-      "content": "[MASK]",
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "@user",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<hashtag>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "</hashtag>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<cashtag>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "</cashtag>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<emoji>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "</emoji>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<http>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "</http>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<email>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -41,25 +122,16 @@
       "special": true
     }
   },
+  "bos_token": "<s>",
   "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]"
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
 }