đ Fikri - Turkish Language Model
Fikri is a language model specifically designed for Turkish language tasks. It is fine - tuned with a specialized dataset, making it efficient and suitable for various Turkish language applications.
⨠Features
- Specialized for Turkish: Trained with high - quality Turkish text data, it can handle Turkish language nuances well.
- Lightweight: With 8 billion parameters, it is relatively small and efficient.
- Versatile Applications: Suitable for tasks such as text understanding, generation, and summarization.
đĻ Installation
No installation steps are provided in the original document, so this section is skipped.
đģ Usage Examples
No code examples are provided in the original document, so this section is skipped.
đ Documentation
Model Overview
| Property |
Details |
| Model Name |
Fikri |
| Model Type |
Language Model |
| Language |
Turkish |
| Model Size |
8B parameters |
| Base Model |
Llama 3.1 |
| Development Hardware |
2x NVIDIA RTX 4090 GPU |
| Description |
Fikri, meaning "intellectual" or "of thought" in Turkish. This model is one of our smallest models trained with a specialized dataset for Turkish tasks. |
| Influencing Paper |
LoRA Learns Less and Forgets Less |
Model Architecture
- Base Model: Llama 3.1 8B
- Base Model Fine - tuning Data Size: ~1 billion high - quality Turkish text units
- Command Training Data Size: 200k Turkish command sets
Training Information
Training Statistics
- Loss: 0.996
- Training Time: (~24 hours)
- Epoch: 1.0
Lora Configuration
r = 128lora_alpha = 32learning_rate = 5e-5
Usage
Fikri is primarily designed for tasks requiring understanding and generation of Turkish text. Its simple configuration and optimized training data enable efficient and appropriate use of the Turkish language in various applications, from text - generation - based AI applications to text summarization.
Acknowledgments
Fikri is a model produced to develop the capabilities of artificial intelligence in the Turkish language and culture, aiming to increase limited Turkish resources. If you have any questions, feedback, or need support, feel free to contact our development team.
Brew Interactive/AI Guild
https://brewww.com
đ§ Technical Details
The model uses Llama 3.1 as the base model and is fine - tuned with Turkish - specific data. The LoRA configuration (r = 128, lora_alpha = 32, learning_rate = 5e-5) is used during training to adapt the model to Turkish language tasks.
đ License
The model is licensed under llama3.1.
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
Transformers