Instructions to use OpenGVLab/ASMv2-Stage2-Pretrain with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/ASMv2-Stage2-Pretrain with Transformers:

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

pipe = pipeline("text-generation", model="OpenGVLab/ASMv2-Stage2-Pretrain")

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("OpenGVLab/ASMv2-Stage2-Pretrain")
model = AutoModelForCausalLM.from_pretrained("OpenGVLab/ASMv2-Stage2-Pretrain")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpenGVLab/ASMv2-Stage2-Pretrain with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/ASMv2-Stage2-Pretrain"
# 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-Stage2-Pretrain",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OpenGVLab/ASMv2-Stage2-Pretrain

SGLang

How to use OpenGVLab/ASMv2-Stage2-Pretrain 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-Stage2-Pretrain" \
    --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-Stage2-Pretrain",
		"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-Stage2-Pretrain" \
        --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-Stage2-Pretrain",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OpenGVLab/ASMv2-Stage2-Pretrain with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/ASMv2-Stage2-Pretrain
```

Weiyun1025 commited on Feb 29, 2024

Commit

87089e3

verified ·

1 Parent(s): 9850ee9

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -12,7 +12,7 @@ Check out the instructions [here](https://github.com/OpenGVLab/all-seeing/tree/m
 **Model type:**
 ASMv2 is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on multimodal instruction-following data.
-It integrates the Scene Graph Conversation (SGC) 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:**

 **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:**