from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

# Load base model
base_model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Llama-3.1-8B-Instruct",
    device_map="auto",
    torch_dtype="auto"
)

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "alantandrea/wiff-expert-llama3.1-8b-lora")
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.1-8B-Instruct")

# Generate
prompt = "Your question here"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Quantized Usage (Lower VRAM)

Base Model: <a href="https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct" target="_blank" rel="noopener noreferrer" class="text-blue-400 hover:text-blue-300 underline underline-offset-2 transition-colors">meta-llama/Llama-3.1-8B-Instruct
Adapter Type: LoRA (Low-Rank Adaptation)
Training Pipeline: GraphRAG + Fine-Tuning
Created: 2026-01-12

python

from transformers import AutoModelForCausalLM, BitsAndBytesConfig
import torch

# 4-bit quantization for ~6GB VRAM
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_compute_dtype=torch.float16
)

base_model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Llama-3.1-8B-Instruct",
    quantization_config=bnb_config,
    device_map="auto"
)

model = PeftModel.from_pretrained(base_model, "alantandrea/wiff-expert-llama3.1-8b-lora")

License

This adapter is released under the Apache 2.0 license. The base model may have its own license terms.