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

Libraries

How to use MBZUAI/GLaMM-GranD-Pretrained with Transformers:

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

pipe = pipeline("text-generation", model="MBZUAI/GLaMM-GranD-Pretrained")

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("MBZUAI/GLaMM-GranD-Pretrained")
model = AutoModelForCausalLM.from_pretrained("MBZUAI/GLaMM-GranD-Pretrained")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MBZUAI/GLaMM-GranD-Pretrained with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MBZUAI/GLaMM-GranD-Pretrained"
# 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-GranD-Pretrained",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MBZUAI/GLaMM-GranD-Pretrained

SGLang

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

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

GLaMM-GranD-Pretrained / added_tokens.json

mmaaz60

Upload folder using huggingface_hub

f30420f over 2 years ago

raw

history blame contribute delete

137 Bytes

	{
	"</p>": 32006,
	"<bbox>": 32002,
	"<im_end>": 32001,
	"<im_start>": 32000,
	"<p>": 32005,
	"<point>": 32003,
	"[SEG]": 32004
	}