Instructions to use Mantis-VL/mfuyu_llava50k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mantis-VL/mfuyu_llava50k with Transformers:

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

pipe = pipeline("text-generation", model="Mantis-VL/mfuyu_llava50k")

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

processor = AutoProcessor.from_pretrained("Mantis-VL/mfuyu_llava50k")
model = AutoModelForCausalLM.from_pretrained("Mantis-VL/mfuyu_llava50k", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Mantis-VL/mfuyu_llava50k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mantis-VL/mfuyu_llava50k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mantis-VL/mfuyu_llava50k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Mantis-VL/mfuyu_llava50k

SGLang

How to use Mantis-VL/mfuyu_llava50k 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 "Mantis-VL/mfuyu_llava50k" \
    --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": "Mantis-VL/mfuyu_llava50k",
		"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 "Mantis-VL/mfuyu_llava50k" \
        --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": "Mantis-VL/mfuyu_llava50k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Mantis-VL/mfuyu_llava50k with Docker Model Runner:
```
docker model run hf.co/Mantis-VL/mfuyu_llava50k
```

mfuyu_llava50k / tokenizer.json

Dongfu Jiang

Upload 6 files

069d2e6 verified almost 3 years ago

History Blame Contribute Delete

16.5 MB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: aae3fb724d841812f69332d62d0b913dcf5306e7085ac5647775b5f5d6c9fb64
Size of remote file:: 16.5 MB
SHA256:: bb11fe58d631a8074842804c2fb73d107fcf56458a3898b7ad5b1894e73fe5fa

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.