Base Model: meta-llama/Llama-3.2-3B-Instruct
Fine-tuning Method: LoRA with rank=8, alpha=20
Training: 2000 iterations on curated motivational quotes dataset
Task: Generating personalized motivational advice and inspirational guidance

Usage

python

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

# Load base model and tokenizer
base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-3B-Instruct")
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-3B-Instruct")

# Load LoRA adapters
model = PeftModel.from_pretrained(base_model, "balazsthomay/llama-3.2-3b-motivational-quotes-lora")

# Generate motivational advice
prompt = "Give me advice about perseverance"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=150)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)

Training Data

The model was trained on a carefully curated dataset of motivational quotes with theme-based labeling for improved contextual understanding.