Instructions to use autotrust/JEV-27B-VL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use autotrust/JEV-27B-VL with Transformers:

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

pipe = pipeline("image-text-to-text", model="autotrust/JEV-27B-VL")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("autotrust/JEV-27B-VL")
model = AutoModelForMultimodalLM.from_pretrained("autotrust/JEV-27B-VL", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use autotrust/JEV-27B-VL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "autotrust/JEV-27B-VL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "autotrust/JEV-27B-VL",
		"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/autotrust/JEV-27B-VL

SGLang

How to use autotrust/JEV-27B-VL 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 "autotrust/JEV-27B-VL" \
    --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": "autotrust/JEV-27B-VL",
		"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 "autotrust/JEV-27B-VL" \
        --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": "autotrust/JEV-27B-VL",
		"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 autotrust/JEV-27B-VL with Docker Model Runner:
```
docker model run hf.co/autotrust/JEV-27B-VL
```

Why no mlx inference support for decision models like this?

by Narutoouz - opened 1 day ago

Discussion

Narutoouz

1 day ago

•

edited 1 day ago

please make a mlx model for this and share it mlx inference engines to support this ideal mlx model made by mlx community

AutoTrustAILab

AutoTrust AI Lab org about 15 hours ago

https://huggingface.co/autotrust/GEV-26B-Decide/discussions/1 @Narutoouz - @Avicennasis just provided a great MLX build for this decision model. We are short of hands and would appreciate if the community can contribute to this MLX gap. BTW, we are just releasing a quantized version of GEV-26B-Decide https://huggingface.co/autotrust/GEV-26B-Decide-NVFP4. You can try this out as well.

ironbcc

about 11 hours ago

@Narutoouz Related, though not a JEV build: I built Seb-9B, a smaller (9B) decision model that already runs on Apple silicon through mlx-lm: https://huggingface.co/ironbcc/seb-9b

The card's MLX snippet reads the probability of each option key from a single forward pass. On an M5 Max, text decisions measured p50 88 ms in bf16 and 104 ms with an 8-bit copy (8.9 GB). That MLX snippet covers text; for image decisions on a Mac, the GGUF build with its vision projector in llama.cpp measured p50 255 ms on 100 image rows. I haven't compared it head-to-head with JEV-27B-VL, so this is an option for local Mac use, not a replacement claim.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment