Instructions to use andyqmongo/IRPO-mvtec-checkpoints with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use andyqmongo/IRPO-mvtec-checkpoints with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="andyqmongo/IRPO-mvtec-checkpoints")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("andyqmongo/IRPO-mvtec-checkpoints", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use andyqmongo/IRPO-mvtec-checkpoints with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "andyqmongo/IRPO-mvtec-checkpoints"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "andyqmongo/IRPO-mvtec-checkpoints",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/andyqmongo/IRPO-mvtec-checkpoints

SGLang

How to use andyqmongo/IRPO-mvtec-checkpoints with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "andyqmongo/IRPO-mvtec-checkpoints" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "andyqmongo/IRPO-mvtec-checkpoints",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "andyqmongo/IRPO-mvtec-checkpoints" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "andyqmongo/IRPO-mvtec-checkpoints",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use andyqmongo/IRPO-mvtec-checkpoints with Docker Model Runner:
```
docker model run hf.co/andyqmongo/IRPO-mvtec-checkpoints
```

IRPO — MVTec checkpoints

Fine-tuned checkpoints of Qwen/Qwen3-VL-8B-Instruct from the IRPO project (inductive-stage experiments), trained on the MVTec-AD category set. Research artifacts; optimizer state stripped (inference/eval weights only).

subfolder	training	type
`sft-mvtec`	supervised fine-tuning (direct answer)	full model
`rft-mvtec`	GRPO / RFT (answer-only), continued run	full model
`ovr-mvtec-lora`	OVR (one-vs-rest rule-induction reward), 468 steps	LoRA adapter
`ovr6-mvtec-lora`	OVR (one-vs-rest rule-induction reward), 234 steps	LoRA adapter
`sftovr-mvtec-lora`	SFT -> OVR	LoRA adapter

Full models: load with transformers.AutoModelForImageTextToText. LoRA adapters: load the base model, then apply with peft.PeftModel.from_pretrained. Base model: Qwen/Qwen3-VL-8B-Instruct.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for andyqmongo/IRPO-mvtec-checkpoints

Base model

Qwen/Qwen3-VL-8B-Instruct

Adapter

(142)

this model