added more details to model

README.md

@@ -3,40 +3,61 @@ library_name: transformers
 license: mit
 base_model: openai-community/gpt2
 tags:
-- generated_from_trainer
+  - generated_from_trainer
 model-index:
-- name: arabic-nano-gpt-v1
-  results: []
+  - name: arabic-nano-gpt-v1
+    results: []
 datasets:
-- wikimedia/wikipedia
+  - wikimedia/wikipedia
 language:
-- ar
+  - ar
 ---
 
-
 # arabic-nano-gpt-v1
 
-This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset.
-It achieves the following results on the held-out test set:
+This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on the arabic [wikimedia/wikipedia](https://huggingface.co/datasets/wikimedia/wikipedia) dataset.
+
+Repository on GitHub: [e-hossam96/arabic-nano-gpt](https://github.com/e-hossam96/arabic-nano-gpt.git)
+
+The model achieves the following results on the held-out test set:
+
 - Loss: 3.02885
 
-## Model description
+## How to Use
 
-More information needed
+```python
+import torch
+from transformers import pipeline
 
-## Intended uses & limitations
+model_ckpt = "e-hossam96/arabic-nano-gpt-v1"
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
-More information needed
 
-## Training and evaluation data
+lm = pipeline(task="text-generation", model=model_ckpt, device=device)
+
+prompt = """المحرك النفاث هو محرك ينفث الموائع (الماء أو الهواء) بسرعة فائقة \
+لينتج قوة دافعة اعتمادا على مبدأ قانون نيوتن الثالث للحركة. \
+هذا التعريف الواسع للمحركات النفاثة يتضمن أيضا"""
+
+output = lm(prompt, max_new_tokens=128)
+
+print(output[0]["generated_text"])
+```
 
-More information needed
+## Model description
+
+- Embedding Size: 384
+- Attention Heads: 4
+- Attention Layers: 4
 
-## Training procedure
+## Training and evaluation data
 
-### Training hyperparameters
+The entire wikipedia dataset was split into three splits based on the 90-5-5 ratios.
+
+## Training hyperparameters
 
 The following hyperparameters were used during training:
+
 - learning_rate: 0.0002
 - train_batch_size: 32
 - eval_batch_size: 32
@@ -48,63 +69,17 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_ratio: 0.01
 - num_epochs: 24
 
-<!-- ### Training results -->
-
-<!-- | Training Loss | Epoch   | Step   | Validation Loss |
-|:-------------:|:-------:|:------:|:---------------:|
-| 4.1743        | 0.5849  | 5000   | 3.6616          |
-| 3.6165        | 1.1698  | 10000  | 3.4256          |
-| 3.5241        | 1.7547  | 15000  | 3.3273          |
-| 3.4341        | 2.3396  | 20000  | 3.2706          |
-| 3.4023        | 2.9245  | 25000  | 3.2331          |
-| 3.3652        | 3.5094  | 30000  | 3.2024          |
-| 3.347         | 4.0943  | 35000  | 3.1826          |
-| 3.3223        | 4.6791  | 40000  | 3.1637          |
-| 3.3107        | 5.2640  | 45000  | 3.1526          |
-| 3.2985        | 5.8489  | 50000  | 3.1370          |
-| 3.2873        | 6.4338  | 55000  | 3.1296          |
-| 3.2758        | 7.0187  | 60000  | 3.1190          |
-| 3.2686        | 7.6036  | 65000  | 3.1105          |
-| 3.2568        | 8.1885  | 70000  | 3.1042          |
-| 3.2546        | 8.7734  | 75000  | 3.0982          |
-| 3.248         | 9.3583  | 80000  | 3.0925          |
-| 3.2431        | 9.9432  | 85000  | 3.0881          |
-| 3.2371        | 10.5281 | 90000  | 3.0820          |
-| 3.2346        | 11.1130 | 95000  | 3.0784          |
-| 3.2273        | 11.6979 | 100000 | 3.0747          |
-| 3.2207        | 12.2828 | 105000 | 3.0701          |
-| 3.2191        | 12.8677 | 110000 | 3.0665          |
-| 3.2148        | 13.4526 | 115000 | 3.0638          |
-| 3.2132        | 14.0374 | 120000 | 3.0594          |
-| 3.2079        | 14.6223 | 125000 | 3.0580          |
-| 3.204         | 15.2072 | 130000 | 3.0549          |
-| 3.2035        | 15.7921 | 135000 | 3.0512          |
-| 3.1999        | 16.3770 | 140000 | 3.0473          |
-| 3.2001        | 16.9619 | 145000 | 3.0462          |
-| 3.1957        | 17.5468 | 150000 | 3.0432          |
-| 3.1948        | 18.1317 | 155000 | 3.0417          |
-| 3.19          | 18.7166 | 160000 | 3.0394          |
-| 3.1873        | 19.3015 | 165000 | 3.0384          |
-| 3.1848        | 19.8864 | 170000 | 3.0367          |
-| 3.1826        | 20.4713 | 175000 | 3.0334          |
-| 3.1839        | 21.0562 | 180000 | 3.0325          |
-| 3.1818        | 21.6411 | 185000 | 3.0314          |
-| 3.1775        | 22.2260 | 190000 | 3.0295          |
-| 3.1747        | 22.8109 | 195000 | 3.0284          |
-| 3.1724        | 23.3957 | 200000 | 3.0273          |
-| 3.1757        | 23.9806 | 205000 | 3.0267          | -->
-
-### Training Loss
-
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/63ccee86374057a338e03c1e/WIQvnj-VCCBqvsUlJZ1K_.png)
-
-### Validation Loss
-
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/63ccee86374057a338e03c1e/DmTh4sIODlv1wrxXcedxL.png)
-
-### Framework versions
+## Training Loss
+
+![Training Loss](assets/arabic-nano-gpt-v1-train-loss.png)
+
+## Validation Loss
+
+![Validation Loss](assets/arabic-nano-gpt-v1-eval-loss.png)
+
+## Framework versions
 
 - Transformers 4.45.2
 - Pytorch 2.5.0
 - Datasets 3.0.1
-- Tokenizers 0.20.1
+- Tokenizers 0.20.1