Flex-VL-32B-LoRA

sungnyun/Flex-VL-32B-LoRA

Flex-VL-32B-LoRA is a machine learning model from sungnyun. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.

Downloads · 30 days

5% of all-time downloads

All-time downloads

Public

Repo size

280 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors269 MB · 94%

At a glance

Library: peft
Access: Public
Created: Jul 31, 2025
Updated: Aug 7, 2025
SHA: 29ef994a

Base models

Qwen/Qwen2.5-VL-32B-Instruct

Model card

From the Hugging Face model README

Model Card for Model ID

Based on Flex-Judge

📖 Usage Instructions:
============================================================
To use this LoRA adapter:

import torch
from transformers import AutoTokenizer, Qwen2_5_VLForConditionalGeneration
from peft import PeftModel

# Load base model
base_model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    "Qwen/Qwen2.5-VL-32B-Instruct",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "sungnyun/Flex-VL-32B-LoRA")

# Load tokenizer
tokenizer = AutoTokenizer.from_pretrained("sungnyun/Flex-VL-32B-LoRA")

Framework versions

PEFT 0.15.2

Library: peft
Created: Jul 31, 2025
Updated: Aug 7, 2025