Instructions to use MeerDevelopment/Qevi-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MeerDevelopment/Qevi-2B with Transformers:

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

pipe = pipeline("image-text-to-text", model="MeerDevelopment/Qevi-2B")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("MeerDevelopment/Qevi-2B")
model = AutoModelForMultimodalLM.from_pretrained("MeerDevelopment/Qevi-2B", device_map="auto")
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 Settings

vLLM

How to use MeerDevelopment/Qevi-2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MeerDevelopment/Qevi-2B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MeerDevelopment/Qevi-2B",
		"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/MeerDevelopment/Qevi-2B

SGLang

How to use MeerDevelopment/Qevi-2B 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 "MeerDevelopment/Qevi-2B" \
    --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": "MeerDevelopment/Qevi-2B",
		"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 "MeerDevelopment/Qevi-2B" \
        --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": "MeerDevelopment/Qevi-2B",
		"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"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use MeerDevelopment/Qevi-2B with Docker Model Runner:
```
docker model run hf.co/MeerDevelopment/Qevi-2B
```

zandervdm commited on 7 days ago

Commit

1150501

verified ·

1 Parent(s): f41579d

Credit TypeSafe Jev as the inspiration; add structured-output tags

Browse files

Files changed (1) hide show

README.md +27 -0

README.md CHANGED Viewed

@@ -7,6 +7,9 @@ tags:
   - vision-language
   - image-classification
   - calibrated-probabilities
   - qwen3-vl
 ---
@@ -330,6 +333,30 @@ per question rather than another full forward pass each.
 The three files have no dependency on this repo's layout. Copy `qevi/` into your own project and
 `import qevi` directly; only `torch`, `transformers` and `pillow` are required.
 ## Citation
 ```bibtex

   - vision-language
   - image-classification
   - calibrated-probabilities
+  - structured-outputs
+  - typed-questions
+  - jev-inspired
   - qwen3-vl
 ---
 The three files have no dependency on this repo's layout. Copy `qevi/` into your own project and
 `import qevi` directly; only `torch`, `transformers` and `pillow` are required.
+## Inspiration and prior art
+Qevi is an **independent, unaffiliated** implementation, for images, of an idea published by
+[TypeSafe](https://typesafe.ai). Their "System One" model **Jev** answers typed questions with
+type-safe structured values and calibrated probabilities rather than generating text: as they put
+it, *"possible outputs and structure are defined in advance, the model never makes type errors,
+all answers are accompanied with calibrated probabilities and confidence scores."*
+Jev is a text model. Qevi asks the same question of images: if the answer is known in advance to
+be one of a small fixed set, why make a vision-language model write a sentence to say it?
+The name reflects the debt. This project began as **JEVI**, short for *Jev for images*, and was
+later renamed Qevi (Qwen + Jevi) once it settled on a Qwen3-VL trunk.
+**What is and is not shared.** The idea of typed, calibrated, non-generative outputs comes from
+TypeSafe's public writing. Everything here is otherwise independent: no code, weights, data or
+training method from TypeSafe is used, and this model is not endorsed by or affiliated with them.
+In particular Qevi does **not** implement their RLCD training method: it is trained with ordinary
+cross-entropy over candidate-answer logits with label smoothing, which is a proper scoring rule
+and is what produces the calibration improvements reported above.
+TypeSafe's published notes on Jev's failure modes (literal reading of questions, unreliable
+counting) informed how this corpus was built and what this model does not claim to do.
 ## Citation
 ```bibtex