Instructions to use TIGER-Lab/Mantis-8B-Fuyu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TIGER-Lab/Mantis-8B-Fuyu with Transformers:

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

pipe = pipeline("text-generation", model="TIGER-Lab/Mantis-8B-Fuyu")

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("TIGER-Lab/Mantis-8B-Fuyu")
model = AutoModelForCausalLM.from_pretrained("TIGER-Lab/Mantis-8B-Fuyu", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TIGER-Lab/Mantis-8B-Fuyu with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TIGER-Lab/Mantis-8B-Fuyu"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TIGER-Lab/Mantis-8B-Fuyu",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TIGER-Lab/Mantis-8B-Fuyu

SGLang

How to use TIGER-Lab/Mantis-8B-Fuyu 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 "TIGER-Lab/Mantis-8B-Fuyu" \
    --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": "TIGER-Lab/Mantis-8B-Fuyu",
		"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 "TIGER-Lab/Mantis-8B-Fuyu" \
        --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": "TIGER-Lab/Mantis-8B-Fuyu",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TIGER-Lab/Mantis-8B-Fuyu with Docker Model Runner:
```
docker model run hf.co/TIGER-Lab/Mantis-8B-Fuyu
```

Mantis-8B-Fuyu / preprocessor_config.json

DongfuJiang

Duplicate from MFuyu/mfuyu_1.5_8b_8192_720p

d192fe8 verified over 2 years ago

Raw

History Blame Contribute Delete

814 Bytes

	{
	"_valid_processor_keys": [
	"images",
	"do_resize",
	"size",
	"resample",
	"do_pad",
	"padding_value",
	"padding_mode",
	"do_normalize",
	"image_mean",
	"image_std",
	"do_rescale",
	"rescale_factor",
	"patch_size",
	"return_tensors",
	"data_format",
	"input_data_format"
	],
	"do_normalize": true,
	"do_pad": true,
	"do_rescale": true,
	"do_resize": true,
	"image_mean": 0.5,
	"image_processor_type": "FuyuImageProcessor",
	"image_std": 0.5,
	"padding_mode": "constant",
	"padding_value": 1.0,
	"patch_size": {
	"height": 30,
	"width": 30
	},
	"processor_class": "MFuyuProcessor",
	"resample": 2,
	"rescale_factor": 0.00392156862745098,
	"size": {
	"height": 720,
	"width": 1290
	},
	"target_height": 1080,
	"target_width": 1920
	}