Upload model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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 +1,190 @@
+---
+language:
+- id
+- eng
+library_name: transformers
+pipeline_tag: text-classification
+tags:
+- text-classification
+- spam-detection
+- indonesian
+- multilingual
+- xlm-roberta
+- social-media
+license: apache-2.0
+metrics:
+- accuracy
+- f1
+base_model:
+- FacebookAI/xlm-roberta-base
+---
+
+# Spam Detection for Social Media Text  
+**Multilingual Indonesian & English | XLM-RoBERTa**
+
+This model is a fine-tuned **XLM-RoBERTa** designed to detect **Spam vs Ham** content in social media text.  
+It supports **Indonesian** and **English Languages**, making it suitable for multi-platform moderation use cases such as Twitter/X, Instagram, TikTok, Facebook, and online forums.
+
+---
+
+## ✨ Key Features
+
+- ✅ Spam vs Ham classification  
+- 🌏 Multilingual support (Indonesian & English)  
+- 🧠 Based on **XLM-RoBERTa (multilingual transformer)**  
+- ⚡ Ready-to-use with Hugging Face `pipeline`  
+- 📊 Strong performance on noisy social media text  
+
+---
+
+## 🌍 Supported Languages
+
+- 🇮🇩 Bahasa Indonesia  
+- 🇬🇧 English  
+
+---
+
+## 🧪 Model Performance
+
+| Metric              | Score  |
+|---------------------|--------|
+| Accuracy            | 0.9645 |
+| F1 (Macro)          | 0.9639 |
+| F1 (Weighted)       | 0.9700 |
+| Precision           | 0.9700 |
+| Recall              | 0.9600 |
+| Training Loss       | 0.0637 |
+| Validation Loss     | 0.1242 |
+
+> Evaluated on held-out validation data with balanced spam/ham distribution.
+
+---
+
+## 🚀 Quick Start
+
+### Installation
+```bash
+pip install transformers torch
+````
+
+### Single Prediction
+
+```python
+from transformers import pipeline
+
+classifier = pipeline(
+    task="text-classification",
+    model="nahiar/spam-detection-xlm-roberta-v1"
+)
+
+result = classifier("PASTI DIJAMIN WDP 100%")
+print(result)
+```
+
+**Output**
+
+```python
+[{'label': 'LABEL_1', 'score': 0.9876}]
+```
+
+### Label Mapping
+
+```text
+LABEL_0 → SPAM
+LABEL_1 → HAM
+```
+
+---
+
+## 📦 Batch Inference Example
+
+```python
+"texts": [
+        "साइबर हमले के बाद JLR का बड़ा बयान - जानें कंपनी ने क्या कहा | Tata Motors के शेयर पर दिखेगा असर?
+
+#TataMotors #JLR #CyberAttack 
+
+https://t.co/6WlGS77UUp",
+        "Kita sudah Ready skrg ini bagi yang memerlukan jasa pemulihan akun & Hapus All akun 
+
+ Lacak lokasi / sadap wa / Hack Akun / Revengeporn - korban pemerasan vcs / terror
+
+TIKTOK,GMAIL,TWITER,TELEGRAM,
+FACEBOOK,INSTAGRAM 
+#revengeporn #zonauangᅠᅠᅠ 
+ ☎️ https://t.co/K0AbW08qnU https://t.co/4IpWNA7a0z",
+        "💥Slot Gacor Hari ini Rute303
+💥Jaminan Jackpot Maxwin malam ini
+
+LINK SLOT GACOR HARI INI : https://t.co/QvxjCAnt8o
+
+Tags:
+Jumbo #timsekop Jumat gratis ongkir Like Crazy PSIM https://t.co/ukuRdlvgGA"
+    ]
+
+results = classifier(texts)
+
+for text, result in zip(texts, results):
+    print(f"{text} -> {result['label']} ({result['score']:.4f})")
+```
+
+---
+
+## 🏗️ Training Configuration
+
+| Parameter          | Value            |
+| ------------------ | ---------------- |
+| Base Model         | xlm-roberta-base |
+| Training Samples   | 22,243           |
+| Validation Samples | 5,561            |
+| Epochs             | 3                |
+| Learning Rate      | 2e-5             |
+| Batch Size         | 16               |
+| Training Date      | 2026-01-21       |
+
+---
+
+## 🎯 Intended Use Cases
+
+* Social media spam moderation
+* Comment & post filtering
+* Content quality control
+* Pre-filtering for sentiment or topic analysis pipelines
+
+---
+
+## ⚠️ Limitations
+
+* Binary classification only (Spam / Ham)
+* Not optimized for non-social-media formal text
+* Performance may degrade on very short or ambiguous messages
+
+---
+
+## 📜 License
+
+Released under the **Apache 2.0 License**.
+Free for commercial and research use.
+
+---
+
+## 📚 Citation
+
+If you use this model in your work, please cite:
+
+```bibtex
+@misc{djunaedi2026spam,
+  author    = {AI/ML Engineer ADS Digital Partner},
+  title     = {Spam Detection for Social Media Text},
+  year      = {2025},
+  publisher = {Hugging Face},
+  url       = {https://huggingface.co/nahiar/spam-detection-xlm-roberta-v1}
+}
+```
+
+---
+
+## 🙌 Acknowledgements
+
+* Hugging Face Transformers
+* Facebook AI Research — XLM-RoBERTa

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.57.6",
+  "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 sha256:11f093db377f3b703cfc7118cdc9dd4e6cbcfb115199cfe864f8691344c6451d
+size 1112208084

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17ba7a4eee75dffa4ee00e5cdf62d8813b0e9fc0930c53087869f0f693b96f26
+size 2224539019

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f806cb7ce9eb8a3b06b4e9b29c4fedbba14df0bec195e5ab719d01674f52f80f
+size 14645

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa0408efb69cab96d5bab9a1aaf44cedbc9fc8d34f4cef378d81605e5c026d5c
+size 1383

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4523e2a162c616b99308e8b035ccb377678042ed451ed80760c3fa70d406f39
+size 1465

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 sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
+size 17082999

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_global_step": 1800,
+  "best_metric": 0.8525679691676576,
+  "best_model_checkpoint": "../model/checkpoint-1800",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 12.545402526855469,
+      "learning_rate": 1.3344444444444446e-05,
+      "loss": 0.593,
+      "step": 600
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.828125,
+      "eval_f1_macro": 0.8270170775916136,
+      "eval_loss": 0.44877034425735474,
+      "eval_runtime": 24.45,
+      "eval_samples_per_second": 196.319,
+      "eval_steps_per_second": 3.067,
+      "step": 600
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 13.457213401794434,
+      "learning_rate": 6.677777777777779e-06,
+      "loss": 0.3861,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8395833333333333,
+      "eval_f1_macro": 0.8393090159160851,
+      "eval_loss": 0.41652506589889526,
+      "eval_runtime": 24.3618,
+      "eval_samples_per_second": 197.029,
+      "eval_steps_per_second": 3.079,
+      "step": 1200
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 22.19487190246582,
+      "learning_rate": 1.1111111111111112e-08,
+      "loss": 0.2759,
+      "step": 1800
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8527083333333333,
+      "eval_f1_macro": 0.8525679691676576,
+      "eval_loss": 0.436837762594223,
+      "eval_runtime": 24.3376,
+      "eval_samples_per_second": 197.226,
+      "eval_steps_per_second": 3.082,
+      "step": 1800
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.51553328611328e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:228ed42715c963d674baf6116246ef1eb14a01f711a10c3c7682a24cc31b1141
+size 5841