Instructions to use Valen-Team/Valen-4B-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Valen-Team/Valen-4B-ONNX with Transformers:

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

pipe = pipeline("image-text-to-text", model="Valen-Team/Valen-4B-ONNX", trust_remote_code=True)
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 AutoModel
model = AutoModel.from_pretrained("Valen-Team/Valen-4B-ONNX", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Valen-Team/Valen-4B-ONNX with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Valen-Team/Valen-4B-ONNX"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Valen-Team/Valen-4B-ONNX",
		"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/Valen-Team/Valen-4B-ONNX

SGLang

How to use Valen-Team/Valen-4B-ONNX 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 "Valen-Team/Valen-4B-ONNX" \
    --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": "Valen-Team/Valen-4B-ONNX",
		"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 "Valen-Team/Valen-4B-ONNX" \
        --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": "Valen-Team/Valen-4B-ONNX",
		"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 Valen-Team/Valen-4B-ONNX with Docker Model Runner:
```
docker model run hf.co/Valen-Team/Valen-4B-ONNX
```

Valen-4B

This is the ONNX version of Valen-Team/Valen-4B.

Valen-4B combines Qwen3.5-4B with a two-layer MLP-Mixer decision head. It predicts probability distributions for Choice, Noul (yes/no), and Score questions. A shared state can contain text, images, or video and serve multiple questions.

Valen-4B 基于 Qwen3.5-4B 和两层 MLP-Mixer 决策头，支持图文、文本、视频，以及共享 state 的多题推理。

Training / 训练

Two-stage SFT: decision-head warmup followed by joint LoRA, Mixer, and visual-merger fine-tuning. We train on millions of samples.
Backbone: BF16. Mixer: FP32. Videos use 16 sampled frames.

Files / 权重格式

Root directory: complete backbone with merged LoRA, trained visual merger, FP32 Mixer, tokenizer, processor, and standalone loading code.

These weights include merged LoRA adapters. BF16 rounding can cause small probability differences from the original training checkpoints used for the reported benchmarks.

Load merged weights / 加载完整合并权重

The verified environment uses Python 3.10, PyTorch 2.6.0, Transformers 5.4.0, torchvision 0.21.0, Pillow, and av 16.1.0. Flash Attention 2 requires a compatible flash-attn installation.

import torch
from transformers import AutoModel

model = AutoModel.from_pretrained(
    "Valen-Team/Valen-4B",
    trust_remote_code=True,
    dtype=torch.bfloat16,
    attn_implementation="sdpa",  # or "flash_attention_2"
).to("cuda").eval()
torch.set_float32_matmul_precision("highest")
torch.backends.cudnn.allow_tf32 = False

response = model.predict({
    "state": "There is one cat in the room.",
    "questions": {
        "animal": {"type": "choice", "instructions": "Which animal is present?",
                   "criteria": {"cat": "A cat", "dog": "A dog"}},
        "is_cat": {"type": "noul", "instructions": "There is a cat in the room."},
    },
}, execution="shared_state")
print(response["answers"])

For a local copy, replace the repository ID with "./Valen-4B". execution="question" scores questions separately. Images and video use the Valen messages, image_url, and video_url schema; relative media paths are resolved against media_root.

Downloads last month: 12

Model tree for Valen-Team/Valen-4B-ONNX

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Quantized

(527)

this model