preparing.ai LoRA adapter
Adapter-only artifact for ivan123-123/preparing.ai (119 MB).
import torch
from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
from peft import PeftModel
base = Qwen2_5_VLForConditionalGeneration.from_pretrained(
"Qwen/Qwen2.5-VL-3B-Instruct", torch_dtype=torch.bfloat16, device_map="auto")
model = PeftModel.from_pretrained(base, "ivan123-123/preparing.ai-lora")
processor = AutoProcessor.from_pretrained("ivan123-123/preparing.ai")
Prefer the full merged model (ivan123-123/preparing.ai) for deployment - it has no extra load step.
- Downloads last month
- 6
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for ivan123-123/preparing.ai-lora
Base model
Qwen/Qwen2.5-VL-3B-Instruct