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 21 days ago

Commit

0fd1ff5

verified ·

1 Parent(s): f178779

Model card: Plan-RewardBench (ACL 2026)

Browse files

Files changed (2) hide show

README.md +10 -1
agent_judge_planrb.png +0 -0

README.md CHANGED Viewed

@@ -66,7 +66,15 @@ 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: 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
@@ -198,6 +206,7 @@ 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 |
 | **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 |

 <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
+**Plan-RewardBench (ACL 2026).** Which of two complete trajectories of a tool-using agent is better? On 1,171 pairs (planning,
+error recovery, safe refusal, tool irrelevance), System 1 reaches **73.2%** macro-average accuracy, the top of the paper's
+table (Table 4): Qwen-Plus 70.0, DeepSeek-V3.2 69.6, Inf-ORM-Llama3.1-70B 69.2, Gemini-3-Flash 69.1, GPT-5 68.5.
+![Plan-RewardBench](agent_judge_planrb.png)
+**AgentRewardBench (2025, with screenshots).**
 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
 | 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** (Plan-RewardBench, ACL 2026, 1,171 pairs) · JEV-27B-VL | **73.2%**, top of the paper's table | Qwen-Plus 70.0 · Gemini-3-Flash 69.1 · GPT-5 68.5 |
 | **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 |

agent_judge_planrb.png ADDED Viewed