ayarlicazhocam-llama-3.2-3b

AyarlicazHocam - Llama 3.2 3B LoRA

This repository contains a LoRA fine-tuned version of Llama 3.2 3B, trained for the AyarlicazHocam AI assistant.

The model is designed to provide conversational assistance related to software engineering, artificial intelligence, university life, and the AyarlicazHocam ecosystem.

Base Model

• Model: unsloth/Llama-3.2-3B
• Fine-tuning: LoRA (PEFT)
• Frameworks: Unsloth, Transformers, TRL

Dataset

The model was fine-tuned on a custom bilingual (Turkish & English) conversational dataset.

Dataset:

• gorkemergune/ayarlicazhocam_finetune

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("gorkemergune/ayarlicazhocam-llama-3.2-3b")
model = AutoModelForCausalLM.from_pretrained("gorkemergune/ayarlicazhocam-llama-3.2-3b")

Training Code

The complete training pipeline, notebooks, and preprocessing scripts are available on GitHub:

https://github.com/gorkemergune/ayarlicazhocam-training

Notes

This project is intended for research, experimentation, and educational purposes.

Author

Görkem Ergüne

• GitHub: https://github.com/gorkemergune
• Hugging Face: https://huggingface.co/gorkemergune
• License:apache-2.0
• Finetuned from model : unsloth/llama-3.2-3b-unsloth-bnb-4bit

This llama model was trained 2x faster with Unsloth

<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>