Instructions to use catlilface/Qwen3.5-0.8B-interrogator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use catlilface/Qwen3.5-0.8B-interrogator with Transformers:

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

pipe = pipeline("image-text-to-text", model="catlilface/Qwen3.5-0.8B-interrogator")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("catlilface/Qwen3.5-0.8B-interrogator")
model = AutoModelForImageTextToText.from_pretrained("catlilface/Qwen3.5-0.8B-interrogator")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use catlilface/Qwen3.5-0.8B-interrogator with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "catlilface/Qwen3.5-0.8B-interrogator"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "catlilface/Qwen3.5-0.8B-interrogator",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/catlilface/Qwen3.5-0.8B-interrogator

SGLang

How to use catlilface/Qwen3.5-0.8B-interrogator 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 "catlilface/Qwen3.5-0.8B-interrogator" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "catlilface/Qwen3.5-0.8B-interrogator",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "catlilface/Qwen3.5-0.8B-interrogator" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "catlilface/Qwen3.5-0.8B-interrogator",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Unsloth Studio new

How to use catlilface/Qwen3.5-0.8B-interrogator with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for catlilface/Qwen3.5-0.8B-interrogator to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for catlilface/Qwen3.5-0.8B-interrogator to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for catlilface/Qwen3.5-0.8B-interrogator to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="catlilface/Qwen3.5-0.8B-interrogator",
    max_seq_length=2048,
)

Docker Model Runner
How to use catlilface/Qwen3.5-0.8B-interrogator with Docker Model Runner:
```
docker model run hf.co/catlilface/Qwen3.5-0.8B-interrogator
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Overview

Inspired by a similar model, this model addresses the same challenge: providing an efficient way to generate questions from raw data. It is highly versatile and requires no specific data formatting; it is even robust enough to handle noisy or low-quality OCR text.

Designed for:

Golden dataset generation
RAG benchmarking
Generating HyDE indices for QnA systems
Evaluation corpus bootstrapping
Retriever quality testing
Graph RAG generation

The model is trained to generate unstructured output consisting of a single atomic question. Due to its small scale, it may struggle to produce correctly formatted structured data (e.g., JSON).

Suggested prompt template

Given the text below, extract ONE question grounded strictly in a single atomic fact.

<text>
<your_text_here>
</text>

Return ONLY the question:

Uploaded finetuned model

Developed by: Catlilface
License: apache-2.0
Finetuned from model : Catlilface/Qwen3.5-0.8B-interrogator

This qwen3_5 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 31

Safetensors

Model size

0.9B params

Tensor type

F32

BF16

Model tree for catlilface/Qwen3.5-0.8B-interrogator

Unable to build the model tree, the base model loops to the model itself. Learn more.

catlilface
/

Qwen3.5-0.8B-interrogator

Overview

Suggested prompt template

Uploaded finetuned model

Model tree for catlilface/Qwen3.5-0.8B-interrogator

Datasets used to train catlilface/Qwen3.5-0.8B-interrogator