Downloads · 30 days
3
15% of all-time downloads
qwen_arabic_medical
Fatma5000/qwen_arabic_medical
qwen_arabic_medical is a text generation model from Fatma5000. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
20
Public
Repo size
2.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.3 GB · 99%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Nov 27, 2025
- Updated
- Nov 27, 2025
- SHA
- ce986f0e
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. -->
qwen_arabic_medical
This model is a fine-tuned version of unsloth/qwen2.5-7b-instruct-unsloth-bnb-4bit on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6825
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: 0.0002
- train_batch_size: 2
- eval_batch_size: 1
- seed: 3407
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7594 | 0.2961 | 250 | 1.7583 |
| 1.6629 | 0.5922 | 500 | 1.6873 |
| 1.6701 | 0.8884 | 750 | 1.6366 |
| 1.3644 | 1.1836 | 1000 | 1.6331 |
| 1.3127 | 1.4797 | 1250 | 1.6502 |
| 1.292 | 1.7758 | 1500 | 1.6292 |
| 1.0995 | 2.0711 | 1750 | 1.6320 |
| 1.1124 | 2.3672 | 2000 | 1.6248 |
| 0.9545 | 2.6633 | 2250 | 1.6714 |
| 0.9728 | 2.9594 | 2500 | 1.6825 |
Framework versions
- PEFT 0.18.0
- Transformers 4.57.2
- Pytorch 2.9.0+cu128
- Datasets 4.3.0
- Tokenizers 0.22.1
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Created
- Nov 27, 2025
- Updated
- Nov 27, 2025