evanto/llama32-1b-xsum-summarizer

LoRA adapter fine-tuned from meta-llama/Llama-3.2-1B-Instruct for compact paragraph summarization.

Intended Use

This adapter is intended for short, faithful summaries of paragraph-style input. It was trained with an instruction prompt and should be loaded with the base model.

Base Model

meta-llama/Llama-3.2-1B-Instruct

Load Example

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base_model = "meta-llama/Llama-3.2-1B-Instruct"
adapter_id = "evanto/llama32-1b-xsum-summarizer"

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

Notes

The adapter was trained on summarization data. It is not a factual search engine and may hallucinate when given very short keywords or incomplete inputs.