Instructions to use MBZUAI/GLaMM-RegCap-RefCOCOg with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MBZUAI/GLaMM-RegCap-RefCOCOg with Transformers:

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

pipe = pipeline("text-generation", model="MBZUAI/GLaMM-RegCap-RefCOCOg")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("MBZUAI/GLaMM-RegCap-RefCOCOg")
model = AutoModelForCausalLM.from_pretrained("MBZUAI/GLaMM-RegCap-RefCOCOg", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MBZUAI/GLaMM-RegCap-RefCOCOg with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MBZUAI/GLaMM-RegCap-RefCOCOg

SGLang

How to use MBZUAI/GLaMM-RegCap-RefCOCOg 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 "MBZUAI/GLaMM-RegCap-RefCOCOg" \
    --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": "MBZUAI/GLaMM-RegCap-RefCOCOg",
		"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 "MBZUAI/GLaMM-RegCap-RefCOCOg" \
        --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": "MBZUAI/GLaMM-RegCap-RefCOCOg",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MBZUAI/GLaMM-RegCap-RefCOCOg with Docker Model Runner:
```
docker model run hf.co/MBZUAI/GLaMM-RegCap-RefCOCOg
```

GLaMM-RegCap-RefCOCOg

Commit History

Dec 13, 2024

13:32
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
3eac2f0

Dec 26, 2023

20:48
Update README.md

mmaaz60

8c84a98
20:35
Update README.md

mmaaz60

0f7ad73
19:19
Update README.md⁠

mmaaz60

485944b
18:33
Upload folder using huggingface_hub

mmaaz60

e9433c1
18:22
initial commit

mmaaz60

fee861b

Commit History

Dec 13, 2024

Adding `safetensors` variant of this model⁠

Dec 26, 2023

Update README.md

Update README.md

Update README.md⁠

Upload folder using huggingface_hub

initial commit