VNU-SecAlign

Model Card

By Minh Đức Đỗ Xuân, published under apache-2.0, revision fcd4ae7e5f16.

checkpoints/finalcheckpoint: LoRA adapter and tokenizer files.

import torch
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

# Config
base_model_id = "meta-llama/Llama-3.1-8B-Instruct"
repo_id = "Jason-42195/VNU-SecAlign"
adapter_subfolder = "checkpoints/final_checkpoint"

# Initialize tokenizer
tokenizer = AutoTokenizer.from_pretrained(base_model_id)

# Load original model
model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    device_map="auto",
    trust_remote_code=True
)

# Load Adapter from subfolder 
model = PeftModel.from_pretrained(
    model,
    repo_id,
    subfolder=adapter_subfolder
)

model.eval()

Identity and Version

Repository

Jason-42195/VNU-SecAlign

Publisher

Minh Đức Đỗ Xuân

Task

Not stated by the source

Modality

Other

Library

Not stated by the source

Parameters

Not stated by the source

Languages

en

Revision

fcd4ae7e5f16044981363db8f41edcab3ba1d762

First published

2026-05-15

Last updated

2026-09-29

Files and Weights

80 files, 6.6 GB in total. The weights are 25 files totalling 6.3 GB in bin, pt, pth, safetensors.

License and Download

License

apache-2.0

Access

Open weights, no gate

Download size

6.3 GB

Built From

• Derived from meta-llama/Llama-3.1-8B-Instruct
• Trained on (disclosed) Jason-42195/VNU-SecAlign

Memory Requirements

Weights only, from the published parameter count; the key-value cache and runtime add to this.