Image-Text-to-Text
Transformers
Safetensors
English
qwen3_5
jev
system-one
system-two
typed-decisions
decision-model
calibrated-probabilities
multimodal
vision
zero-shot
decision-index
recommendation
lora
vllm
conversational
Eval Results
Instructions to use autotrust/AutoTrust-Decider-Pro-Vision-27B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use autotrust/AutoTrust-Decider-Pro-Vision-27B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="autotrust/AutoTrust-Decider-Pro-Vision-27B") 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/AutoTrust-Decider-Pro-Vision-27B") model = AutoModelForMultimodalLM.from_pretrained("autotrust/AutoTrust-Decider-Pro-Vision-27B", 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/AutoTrust-Decider-Pro-Vision-27B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "autotrust/AutoTrust-Decider-Pro-Vision-27B" # 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/AutoTrust-Decider-Pro-Vision-27B", "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/AutoTrust-Decider-Pro-Vision-27B
- SGLang
How to use autotrust/AutoTrust-Decider-Pro-Vision-27B 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/AutoTrust-Decider-Pro-Vision-27B" \ --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/AutoTrust-Decider-Pro-Vision-27B", "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/AutoTrust-Decider-Pro-Vision-27B" \ --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/AutoTrust-Decider-Pro-Vision-27B", "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/AutoTrust-Decider-Pro-Vision-27B with Docker Model Runner:
docker model run hf.co/autotrust/AutoTrust-Decider-Pro-Vision-27B
Model card: Decision Index #1 first, then the model introduction
Browse files
README.md
CHANGED
|
@@ -24,16 +24,6 @@ tags:
|
|
| 24 |
|
| 25 |
# autotrust/JEV-27B-VL
|
| 26 |
|
| 27 |
-
### JEV-27B that can see: the same System 1 decisions and System 2, now on images
|
| 28 |
-
|
| 29 |
-
**autotrust/JEV-27B-VL** is [autotrust/JEV-27B](https://huggingface.co/autotrust/JEV-27B) with vision, and the
|
| 30 |
-
**#1 model on the [Jev Decision Index Vision board](https://huggingface.co/spaces/multimodalart/jev-decision-index?mode=vision)**.
|
| 31 |
-
|
| 32 |
-
| | what it does | output |
|
| 33 |
-
|---|---|---|
|
| 34 |
-
| **System 1** (`POST /v1/decide`) | typed decisions: yes/no · pick one of 2–256 options · rate 0–5, over text and images; prompts up to 256K tokens | a calibrated probability for every option, in one forward pass |
|
| 35 |
-
| **System 2** (`autotrust/JEV-27B-VL`) | the unmodified Qwen3.8-27B, optionally thinking step by step, with image input | text / reasoning |
|
| 36 |
-
|
| 37 |
## #1 on the Decision Index Vision board
|
| 38 |
|
| 39 |
JEV-27B-VL is **ranked first of 20 vision decision models** on the community
|
|
@@ -90,6 +80,16 @@ same skills.
|
|
| 90 |
**In one sentence:** the most accurate of 20 vision decision models, with no weak skill group, first on unseen images,
|
| 91 |
calibrated, fast, and above a 397B model at a fifteenth of the size, from a decision head trained on text alone.
|
| 92 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 93 |
## New (3 October 2026): robot arm and computer use
|
| 94 |
|
| 95 |
Every step below is **one System 1 decision**: a camera image or a screenshot in, a probability for every action out, in
|
|
|
|
| 24 |
|
| 25 |
# autotrust/JEV-27B-VL
|
| 26 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
## #1 on the Decision Index Vision board
|
| 28 |
|
| 29 |
JEV-27B-VL is **ranked first of 20 vision decision models** on the community
|
|
|
|
| 80 |
**In one sentence:** the most accurate of 20 vision decision models, with no weak skill group, first on unseen images,
|
| 81 |
calibrated, fast, and above a 397B model at a fifteenth of the size, from a decision head trained on text alone.
|
| 82 |
|
| 83 |
+
## JEV-27B that can see: the same System 1 decisions and System 2, now on images
|
| 84 |
+
|
| 85 |
+
**autotrust/JEV-27B-VL** is [autotrust/JEV-27B](https://huggingface.co/autotrust/JEV-27B) with vision, and the
|
| 86 |
+
**#1 model on the [Jev Decision Index Vision board](https://huggingface.co/spaces/multimodalart/jev-decision-index?mode=vision)**.
|
| 87 |
+
|
| 88 |
+
| | what it does | output |
|
| 89 |
+
|---|---|---|
|
| 90 |
+
| **System 1** (`POST /v1/decide`) | typed decisions: yes/no · pick one of 2–256 options · rate 0–5, over text and images; prompts up to 256K tokens | a calibrated probability for every option, in one forward pass |
|
| 91 |
+
| **System 2** (`autotrust/JEV-27B-VL`) | the unmodified Qwen3.8-27B, optionally thinking step by step, with image input | text / reasoning |
|
| 92 |
+
|
| 93 |
## New (3 October 2026): robot arm and computer use
|
| 94 |
|
| 95 |
Every step below is **one System 1 decision**: a camera image or a screenshot in, a probability for every action out, in
|