README.md

---
tags:
- unsloth
---

# kevin009/llama323

## Model Description
This is a LoRA-tuned version of unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit using KTO (Knowledge Transfer Optimization).

## Training Parameters
- Learning Rate: 2.5e-05
- Batch Size: 1
- Training Steps: 1300
- LoRA Rank: 16
- Training Date: 2025-01-02

## Usage
```python
from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer

model = AutoPeftModelForCausalLM.from_pretrained("kevin009/llama323", token="YOUR_TOKEN")
tokenizer = AutoTokenizer.from_pretrained("kevin009/llama323")
```