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")

# pip install -U transformers accelerate
# 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
```

DongfuJiang commited on May 3, 2024

Commit

bfb4311

verified ·

1 Parent(s): 22b8d75

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -66,7 +66,8 @@ model = MFuyuForCausalLM.from_pretrained("TIGER-Lab/Mantis-8B-Fuyu", device_map=
 generation_kwargs = {
     "max_new_tokens": 1024,
     "num_beams": 1,
-    "do_sample": False
 }
 # chat

 generation_kwargs = {
     "max_new_tokens": 1024,
     "num_beams": 1,
+    "do_sample": False,
+    "pad_token_id": processor.tokenizer.eos_token_id,
 }
 # chat