cenfis/llama3-8b-tr-finetuned
cenfis/llama3-8b-tr-finetuned is an experimental 8 billion parameter Llama 3 model, fine-tuned specifically for the Turkish language. Developed by cenfis, this model leverages an adapter on Unsloth's Llama 3-8B quantized base, optimized for Turkish language understanding and generation. It is designed for educational and developmental purposes, with ongoing training planned to enhance its capabilities in Turkish.
Loading preview...
Overview
cenfis/llama3-8b-tr-finetuned is an experimental and educational fine-tuned variant of the 8 billion parameter Llama 3 model, specifically adapted for the Turkish language. This model was developed by cenfis, building upon Unsloth's Llama 3-8B quantized model using an adapter-based approach. The project aims to provide a Llama 3 model with enhanced proficiency in Turkish, with plans for continuous development and training as more quality Turkish data becomes available.
Key Capabilities
- Turkish Language Processing: Fine-tuned to understand and generate text in Turkish.
- Llama 3 Architecture: Benefits from the underlying Llama 3 8B parameter architecture.
- Adapter-based Fine-tuning: Utilizes PEFT (Parameter-Efficient Fine-Tuning) for efficient adaptation.
- Quantized Base Model: Built on a 4-bit quantized Llama 3-8B model, potentially offering efficiency benefits.
- Format Availability: Provided in .gguf and .bin formats for compatibility with
llama.cppandvLLM.
Important Usage Notes
- Prompt Template: It is highly recommended to use an Alpaca Prompt Template or a similar structured template to ensure meaningful generations and avoid repetitive outputs.
- Hardware Requirement: Requires a CUDA-supported GPU for optimal performance.
- Development Status: This is an experimental and educational model, open to further development and improvement with additional quality Turkish datasets.