Downloads · 30 days
67
8% of all-time downloads
indicbert-hatespeechdetection-malayalam
ramesh070/indicbert-hatespeechdetection-malayalam
indicbert-hatespeechdetection-malayalam is a text classification model from ramesh070. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
791
Public
Parameters
278M
21.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.1 GB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- bert
- Access
- Public
- Created
- Dec 3, 2025
- Updated
- Dec 3, 2025
- SHA
- e911b193
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
indicbert-hatespeechdetection-malayalam
This model is a fine-tuned version of ai4bharat/IndicBERTv2-MLM-only on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1542
- Accuracy: 0.9773
- F1: 0.9792
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.6004 | 1.0 | 23 | 0.3053 | 0.9545 | 0.9574 |
| 0.2204 | 2.0 | 46 | 0.0778 | 0.9773 | 0.9796 |
| 0.0813 | 3.0 | 69 | 0.0750 | 0.9886 | 0.9897 |
| 0.025 | 4.0 | 92 | 0.0850 | 0.9773 | 0.9792 |
| 0.004 | 5.0 | 115 | 0.1063 | 0.9773 | 0.9792 |
| 0.0016 | 6.0 | 138 | 0.1135 | 0.9773 | 0.9792 |
| 0.0017 | 7.0 | 161 | 0.1255 | 0.9773 | 0.9792 |
| 0.0015 | 8.0 | 184 | 0.1252 | 0.9773 | 0.9792 |
| 0.0006 | 9.0 | 207 | 0.1358 | 0.9773 | 0.9792 |
| 0.0005 | 10.0 | 230 | 0.1398 | 0.9773 | 0.9792 |
| 0.0004 | 11.0 | 253 | 0.1420 | 0.9773 | 0.9792 |
| 0.0004 | 12.0 | 276 | 0.1439 | 0.9773 | 0.9792 |
| 0.0003 | 13.0 | 299 | 0.1467 | 0.9773 | 0.9792 |
| 0.0003 | 14.0 | 322 | 0.1482 | 0.9773 | 0.9792 |
| 0.0005 | 15.0 | 345 | 0.1501 | 0.9773 | 0.9792 |
| 0.0003 | 16.0 | 368 | 0.1519 | 0.9773 | 0.9792 |
| 0.0003 | 17.0 | 391 | 0.1529 | 0.9773 | 0.9792 |
| 0.0003 | 18.0 | 414 | 0.1536 | 0.9773 | 0.9792 |
| 0.0003 | 19.0 | 437 | 0.1541 | 0.9773 | 0.9792 |
| 0.0003 | 20.0 | 460 | 0.1542 | 0.9773 | 0.9792 |
Framework versions
- Transformers 4.53.3
- Pytorch 2.9.1+cu128
- Datasets 4.4.1
- Tokenizers 0.21.2
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- mit
- Created
- Dec 3, 2025
- Updated
- Dec 3, 2025