Instructions to use TIGER-Lab/MAmmoTH-VL2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TIGER-Lab/MAmmoTH-VL2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="TIGER-Lab/MAmmoTH-VL2")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TIGER-Lab/MAmmoTH-VL2")
model = AutoModelForCausalLM.from_pretrained("TIGER-Lab/MAmmoTH-VL2", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TIGER-Lab/MAmmoTH-VL2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TIGER-Lab/MAmmoTH-VL2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TIGER-Lab/MAmmoTH-VL2",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/TIGER-Lab/MAmmoTH-VL2

SGLang

How to use TIGER-Lab/MAmmoTH-VL2 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/MAmmoTH-VL2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TIGER-Lab/MAmmoTH-VL2",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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/MAmmoTH-VL2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TIGER-Lab/MAmmoTH-VL2",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use TIGER-Lab/MAmmoTH-VL2 with Docker Model Runner:
```
docker model run hf.co/TIGER-Lab/MAmmoTH-VL2
```

wenhu commited on May 6, 2025

Commit

b10993f

verified ·

1 Parent(s): 4508e16

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -12

README.md CHANGED Viewed

@@ -65,18 +65,9 @@ image_sizes = [[image.size[0], image.size[1]]]
 prompt = "In the picture shown below, prove ΔWXY and ΔZWY are similar. Please conclude your answer as Answer: xxx at the end if possible."
 # Set up conversation template
-try:
-    conv_template = "qwen_2_5"
-    conv = copy.deepcopy(conv_templates[conv_template])
-except KeyError:
-    available_templates = list(conv_templates.keys())
-    for template_name in available_templates:
-        if 'qwen' in template_name.lower():
-            conv_template = template_name
-            break
-    else:
-        conv_template = available_templates[0]
-    conv = copy.deepcopy(conv_templates[conv_template])
 # Add question with image
 question = DEFAULT_IMAGE_TOKEN + "\n" + prompt

 prompt = "In the picture shown below, prove ΔWXY and ΔZWY are similar. Please conclude your answer as Answer: xxx at the end if possible."
 # Set up conversation template
+conv_template = "qwen_2_5"
+conv = copy.deepcopy(conv_templates[conv_template])
 # Add question with image
 question = DEFAULT_IMAGE_TOKEN + "\n" + prompt