Update README.md
Browse files
README.md
CHANGED
|
@@ -7,6 +7,10 @@ tags:
|
|
| 7 |
model-index:
|
| 8 |
- name: tajik-classifier
|
| 9 |
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -14,21 +18,34 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# tajik-classifier
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on
|
|
|
|
| 18 |
|
| 19 |
-
## Model description
|
| 20 |
|
| 21 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
-
## Intended uses
|
| 24 |
|
| 25 |
-
|
|
|
|
|
|
|
| 26 |
|
| 27 |
-
##
|
|
|
|
|
|
|
| 28 |
|
| 29 |
-
|
| 30 |
|
| 31 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
|
| 33 |
### Training hyperparameters
|
| 34 |
|
|
@@ -42,13 +59,9 @@ The following hyperparameters were used during training:
|
|
| 42 |
- num_epochs: 5
|
| 43 |
- mixed_precision_training: Native AMP
|
| 44 |
|
| 45 |
-
### Training results
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
|
| 49 |
### Framework versions
|
| 50 |
|
| 51 |
- Transformers 4.52.4
|
| 52 |
- Pytorch 2.6.0+cu124
|
| 53 |
- Datasets 3.6.0
|
| 54 |
-
- Tokenizers 0.21.1
|
|
|
|
| 7 |
model-index:
|
| 8 |
- name: tajik-classifier
|
| 9 |
results: []
|
| 10 |
+
datasets:
|
| 11 |
+
- mteb/banking77
|
| 12 |
+
language:
|
| 13 |
+
- tg
|
| 14 |
---
|
| 15 |
|
| 16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 18 |
|
| 19 |
# tajik-classifier
|
| 20 |
|
| 21 |
+
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) trained on a Tajik-translated version of the [Banking77](https://huggingface.co/datasets/mteb/banking77) dataset.
|
| 22 |
+
The dataset contains customer service queries related to banking, classified into 77 different intent categories.
|
| 23 |
|
| 24 |
+
## 🧾 Model description
|
| 25 |
|
| 26 |
+
* **Base model**: XLM-RoBERTa Base
|
| 27 |
+
* **Language**: Tajik (tg)
|
| 28 |
+
* **Task**: Text classification (intent recognition)
|
| 29 |
+
* **Number of classes**: 77
|
| 30 |
+
<p>The model is designed to classify banking-related queries into one of 77 categories such as card_payment, atm_support, balance, lost_or_stolen_card, etc. It is useful for building customer support bots or virtual assistants that operate in the Tajik language.</p>
|
| 31 |
|
| 32 |
+
## ✅ Intended uses
|
| 33 |
|
| 34 |
+
* Banking customer support chatbots for Tajik-speaking users
|
| 35 |
+
* Voice or text-based virtual assistants in the finance domain
|
| 36 |
+
* Automated ticket or query routing in Tajik financial services
|
| 37 |
|
| 38 |
+
## ⚠️ Limitations
|
| 39 |
+
* The model may not generalize well to non-banking topics
|
| 40 |
+
* Classification performance depends on the quality and accuracy of the dataset translation
|
| 41 |
|
| 42 |
+
## 📚 Training and evaluation data
|
| 43 |
|
| 44 |
+
* **Dataset**: Banking77 dataset translated from English to Tajik
|
| 45 |
+
* **Size**: ~13,000 examples across 77 intent classes
|
| 46 |
+
* **Source**: Original banking77 English dataset, translated via machine translation
|
| 47 |
+
|
| 48 |
+
## ⚙️ Training procedure
|
| 49 |
|
| 50 |
### Training hyperparameters
|
| 51 |
|
|
|
|
| 59 |
- num_epochs: 5
|
| 60 |
- mixed_precision_training: Native AMP
|
| 61 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
### Framework versions
|
| 63 |
|
| 64 |
- Transformers 4.52.4
|
| 65 |
- Pytorch 2.6.0+cu124
|
| 66 |
- Datasets 3.6.0
|
| 67 |
+
- Tokenizers 0.21.1
|