MangoLassi/llama-3.2-1b-finetuned

Fine-tuned Llama-3.2-1B Model

This is a fine-tuned version of meta-llama/Llama-3.2-1B with PEFT/LoRA.

Model Details

• Base model: meta-llama/Llama-3.2-1B
• Fine-tuning method: PEFT with LoRA
• Rank (r): 8
• Alpha: 16
• Target modules: q_proj, v_proj

Usage

from transformers import AutoTokenizer
from peft import AutoPeftModelForCausalLM

# Load model and tokenizer
model = AutoPeftModelForCausalLM.from_pretrained("MangoLassi/llama-3.2-1b-finetuned")
tokenizer = AutoTokenizer.from_pretrained("MangoLassi/llama-3.2-1b-finetuned")

# Generate text
prompt = "Your prompt here"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_length=200)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))