Llama-70B-God-Tier-Adapter

LoRA adapter fine-tuned from meta-llama/Llama-3.3-70B-Instruct.

Model Details

• Type: LoRA adapter (requires a compatible base model)
• Base model: meta-llama/Llama-3.3-70B-Instruct
• Dataset: tatsu-lab/alpaca
• Training samples: 1000
• Max sequence length: 512
• Packing: False
• LoRA: r=16, alpha=32, dropout=0.05, target=attn

Intended Use

This repository contains adapter weights intended to be loaded on top of the base model.

Usage (Transformers + PEFT)

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_id = "meta-llama/Llama-3.3-70B-Instruct"
adapter_id = "Daga2001/Llama-70B-God-Tier-Adapter"

tokenizer = AutoTokenizer.from_pretrained(base_id)
base = AutoModelForCausalLM.from_pretrained(base_id, device_map="auto")
model = PeftModel.from_pretrained(base, adapter_id)

License / Attribution

Use is subject to the base model license and terms.