AlignmentResearch/Llama-3.3-Tiny-Instruct-lora-reference-0

Random LoRA Adapter for Reference Model

This is a randomly initialized LoRA adapter for the AlignmentResearch/Llama-3.3-Tiny-Instruct model, specifically designed for use as a reference model.

Details

• Base model: AlignmentResearch/Llama-3.3-Tiny-Instruct
• Adapter type: Reference
• Seed: 0
• LoRA rank: 16
• LoRA alpha: 32
• target modules: all-linear

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load base model
base_model = AutoModelForCausalLM.from_pretrained("AlignmentResearch/Llama-3.3-Tiny-Instruct")
tokenizer = AutoTokenizer.from_pretrained("AlignmentResearch/Llama-3.3-Tiny-Instruct")

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "AlignmentResearch/Llama-3.3-Tiny-Instruct-lora-reference-0")

This reference adapter was created for testing purposes and contains random weights.