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
```

cloudyu commited on 28 days ago

Commit

f178779

verified ·

1 Parent(s): 3ea6d7a

Model card: agent judge (AgentRewardBench)

Browse files

Files changed (2) hide show

README.md +24 -0
agent_judge.png +0 -0

README.md CHANGED Viewed

@@ -66,6 +66,29 @@ about 300 ms per decision (4× playback).
 <video src="https://huggingface.co/autotrust/JEV-27B-VL/resolve/main/videos/vl5.mp4" controls autoplay loop muted playsinline width="100%"></video>
 ## Highlight: multimodal judge
 Given an image, a question and two answers, System 1 says which answer is better, zero-shot and in one forward pass per order.
@@ -175,6 +198,7 @@ Human gold labels (CLINC-150, MTOP, GoEmotions, DBpedia), 800 items.
 | task | result | comparison |
 |---|---|---|
 | **Image recommendation, zero-shot** (MicroLens, covers only) · JEV-27B-VL | **AUC 0.727** | collaborative filtering from 59,045 users' logs 0.728 · titles only 0.649 |
 | **Multimodal judge** (VL-RewardBench, 1,247 pairs) · JEV-27B-VL | **78.3% accuracy**, above every model on its 2025 leaderboard | Skywork-VL-Reward-7B 73.3 · GPT-4o 65.8 · Claude 3.5 Sonnet 55.3 |
 | **Multimodal judge** (MMRB2, 4 × 1,000 pairs) · JEV-27B-VL | text-to-image **69.2**, average **63.8** | GPT-5 70.5 / 72.2 · GPT-4.1 65.8 / 63.5 · GPT-4o 60.3 / 59.7 |
 | **Biomedical research questions** (PubMedQA test, 500) · JEV-27B-VL | **77.8% accuracy**, zero-shot | human experts 78.0% · GPT-4 zero-shot 75.2% · BioBERT 68.1% |

 <video src="https://huggingface.co/autotrust/JEV-27B-VL/resolve/main/videos/vl5.mp4" controls autoplay loop muted playsinline width="100%"></video>
+## Highlight: agent judge (AgentRewardBench)
+Did the web agent really finish the task? Given the user's goal, the agent's actions and final message, and the final
+screenshot, System 1 returns P(task completed) in one forward pass, zero-shot. On
+[AgentRewardBench](https://agent-reward-bench.github.io) (McGill, 2025; 1,302 expert-labelled trajectories from GPT-4o, Claude
+3.7, Llama 3.3 and Qwen2.5-VL agents) its precision is **higher than every judge on the official leaderboard at that judge's own
+recall**:
+| judge | its precision | its recall | **JEV-27B-VL at the same recall** |
+|---|---:|---:|---:|
+| Rule-based | 83.8 | 55.9 | **86.2** |
+| WebJudge (o4-mini) | 82.0 | 47.8 | **87.7** |
+| WebJudge-7B (trained judge) | 75.7 | 58.0 | **86.2** |
+| World-State-Model-7B (trained judge) | 71.2 | 72.2 | **77.7** |
+| GPT-4o (accessibility tree) | 69.8 | 83.1 | **72.9** |
+| Claude 3.7 Sonnet (screenshot) | 69.4 | 76.3 | **75.6** |
+| Qwen2.5-VL-72B (screenshot) | 64.5 | 86.1 | **67.9** |
+At threshold 0.5: precision 78.4, recall 70.2; AUROC 0.91. All 1,302 judgements in about 4 minutes on one GPU. Code:
+[JEV-27B-DEMO / 10-agent-judge](https://github.com/yuhai-china/JEV-27B-DEMO/tree/master/10-agent-judge).
+![agent judge](agent_judge.png)
 ## Highlight: multimodal judge
 Given an image, a question and two answers, System 1 says which answer is better, zero-shot and in one forward pass per order.
 | task | result | comparison |
 |---|---|---|
 | **Image recommendation, zero-shot** (MicroLens, covers only) · JEV-27B-VL | **AUC 0.727** | collaborative filtering from 59,045 users' logs 0.728 · titles only 0.649 |
+| **Agent judge** (AgentRewardBench, 1,302 trajectories) · JEV-27B-VL | **higher precision than all 16 leaderboard judges** at their recall; AUROC 0.91 | o4-mini, GPT-4o, Claude 3.7, trained 7B judges |
 | **Multimodal judge** (VL-RewardBench, 1,247 pairs) · JEV-27B-VL | **78.3% accuracy**, above every model on its 2025 leaderboard | Skywork-VL-Reward-7B 73.3 · GPT-4o 65.8 · Claude 3.5 Sonnet 55.3 |
 | **Multimodal judge** (MMRB2, 4 × 1,000 pairs) · JEV-27B-VL | text-to-image **69.2**, average **63.8** | GPT-5 70.5 / 72.2 · GPT-4.1 65.8 / 63.5 · GPT-4o 60.3 / 59.7 |
 | **Biomedical research questions** (PubMedQA test, 500) · JEV-27B-VL | **77.8% accuracy**, zero-shot | human experts 78.0% · GPT-4 zero-shot 75.2% · BioBERT 68.1% |

agent_judge.png ADDED Viewed