Update README.md
Browse files
README.md
CHANGED
|
@@ -12,4 +12,17 @@ tags:
|
|
| 12 |
language:
|
| 13 |
- ar
|
| 14 |
library_name: peft
|
| 15 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
language:
|
| 13 |
- ar
|
| 14 |
library_name: peft
|
| 15 |
+
---
|
| 16 |
+
## Model Description
|
| 17 |
+
|
| 18 |
+
The model **ayazeyad/llama3.2-3B-fine-tuned-v2** is a fine-tuned version of the Llama-3.2-3B model, tailored for sentiment analysis in Arabic. The model was trained using the Arabic reviews Dataset, which includes a wide range of reviews in Arabic language. This model is ideal for sentiment analysis in Arabic.
|
| 19 |
+
|
| 20 |
+
The training dataset includes Arabic sentences for reviews about the applications's services sourced from kaggle.
|
| 21 |
+
|
| 22 |
+
## Model Details
|
| 23 |
+
|
| 24 |
+
- **Model Type**: Transformer-based language model fine-tuned for text generation
|
| 25 |
+
- **Languages**: Arabic
|
| 26 |
+
- **Base Model**: [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B)
|
| 27 |
+
- **Dataset**: [Arabic-CompanyReviews](https://huggingface.co/datasets/ayazeyad/Arabic-CompanyReviews)
|
| 28 |
+
- **Number of Parameters**: 3 billion
|