sungnyun/Flex-VL-32B-LoRA

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