Instructions to use Stanley11/Beyond-Visual-Evidence-IDNet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Stanley11/Beyond-Visual-Evidence-IDNet with Transformers:

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

pipe = pipeline("image-text-to-text", model="Stanley11/Beyond-Visual-Evidence-IDNet")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Stanley11/Beyond-Visual-Evidence-IDNet", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Stanley11/Beyond-Visual-Evidence-IDNet with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Stanley11/Beyond-Visual-Evidence-IDNet"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Stanley11/Beyond-Visual-Evidence-IDNet",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Stanley11/Beyond-Visual-Evidence-IDNet

SGLang

How to use Stanley11/Beyond-Visual-Evidence-IDNet 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 "Stanley11/Beyond-Visual-Evidence-IDNet" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Stanley11/Beyond-Visual-Evidence-IDNet",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Stanley11/Beyond-Visual-Evidence-IDNet" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Stanley11/Beyond-Visual-Evidence-IDNet",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Stanley11/Beyond-Visual-Evidence-IDNet with Docker Model Runner:
```
docker model run hf.co/Stanley11/Beyond-Visual-Evidence-IDNet
```

Beyond-Visual-Evidence-IDNet

File size: 706 Bytes

4b500e7

{
  "repo_id": "Stanley11/Beyond-Visual-Evidence-IDNet",
  "method": "Base Model",
  "source_checkpoint": "llava-1.5-7b-idnet-ca-5000-best",
  "base_model": "llava-hf/llava-1.5-7b-hf",
  "parameters": 7063427072,
  "dtype": "BF16",
  "tensor_count": 686,
  "weight_bytes": 14126947704,
  "paper": "https://arxiv.org/abs/2608.12911",
  "code": "https://github.com/xubeining/Beyond-Visual-Evidence",
  "source_inspection_date": "2026-10-25",
  "evaluation_status": "Supplied table; not rerun for this release",
  "paper_reported_metrics": {
    "prompt_acc": 0.933,
    "prompt_lc": 0.938,
    "image_acc": 0.226,
    "image_lc": 0.795,
    "kie_lc": 0.999
  },
  "subfolder": "Base"
}