Instructions to use OpenGVLab/ASMv2-Stage1-Ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/ASMv2-Stage1-Ft with Transformers:

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

pipe = pipeline("text-generation", model="OpenGVLab/ASMv2-Stage1-Ft")

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("OpenGVLab/ASMv2-Stage1-Ft")
model = AutoModelForCausalLM.from_pretrained("OpenGVLab/ASMv2-Stage1-Ft")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenGVLab/ASMv2-Stage1-Ft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/ASMv2-Stage1-Ft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenGVLab/ASMv2-Stage1-Ft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OpenGVLab/ASMv2-Stage1-Ft

SGLang

How to use OpenGVLab/ASMv2-Stage1-Ft 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 "OpenGVLab/ASMv2-Stage1-Ft" \
    --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": "OpenGVLab/ASMv2-Stage1-Ft",
		"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 "OpenGVLab/ASMv2-Stage1-Ft" \
        --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": "OpenGVLab/ASMv2-Stage1-Ft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OpenGVLab/ASMv2-Stage1-Ft with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/ASMv2-Stage1-Ft
```

ASMv2 Model Card

This is a pretrained checkpoint, you can use it to instruct tune your multimodal models.

Check out the instructions here.

Model details

Model type: ASMv2 is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on multimodal instruction-following data. It integrates the Relation Conversation (ReC) ability while maintaining powerful general capabilities. This model is also endowed with grounding and referring capabilities, exhibiting state-of-the-art performance on region-level tasks, and can be naturally adapted to the Scene Graph Generation task in an open-ended manner.

Model date: ASMv2-Pretrain was trained in January 2024.

Paper or resources for more information: https://github.com/OpenGVLab/all-seeing

License

ASMv2-Pretrain is open-sourced under the Apache License 2.0,

Where to send questions or comments about the model: https://github.com/OpenGVLab/all-seeing/issues

Intended use

Primary intended uses: The primary use of ASMv2 is research on large multimodal models and chatbots.

Primary intended users: The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.

Training dataset

The pretrain phase employs 5M filtered samples from CC12M, 10M filtered samples from AS-1B, and 15M filtered samples from GRiT.

See here for more details.

Downloads last month: 33

Collection including OpenGVLab/ASMv2-Stage1-Ft

All-Seeing Project

Collection

11 items • Updated Sep 28, 2025 • 8