Instructions to use allenai/MolmoWeb-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use allenai/MolmoWeb-4B with Transformers:

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

pipe = pipeline("image-text-to-text", model="allenai/MolmoWeb-4B", trust_remote_code=True)
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 AutoModelForImageTextToText
model = AutoModelForImageTextToText.from_pretrained("allenai/MolmoWeb-4B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use allenai/MolmoWeb-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "allenai/MolmoWeb-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "allenai/MolmoWeb-4B",
		"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/allenai/MolmoWeb-4B

SGLang

How to use allenai/MolmoWeb-4B 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 "allenai/MolmoWeb-4B" \
    --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": "allenai/MolmoWeb-4B",
		"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 "allenai/MolmoWeb-4B" \
        --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": "allenai/MolmoWeb-4B",
		"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 allenai/MolmoWeb-4B with Docker Model Runner:
```
docker model run hf.co/allenai/MolmoWeb-4B
```

zixianma02 commited on Mar 30

Commit

733d337

verified ·

1 Parent(s): 018ebe4

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -2

README.md CHANGED Viewed

@@ -59,7 +59,8 @@ checkpoint_dir = "allenai/MolmoWeb-4B"
 model = AutoModelForImageTextToText.from_pretrained(
     checkpoint_dir,
     trust_remote_code=True,
-    dtype="auto",
     device_map="auto",
 )
@@ -122,7 +123,8 @@ inputs = processor.apply_chat_template(
     padding=True,
 )
-inputs = {k: v.to("cuda") for k, v in inputs.items()}
 with torch.inference_mode():
     output = model.generate(**inputs, max_new_tokens=200)

 model = AutoModelForImageTextToText.from_pretrained(
     checkpoint_dir,
     trust_remote_code=True,
+    torch_dtype=torch.float32, # we recommend using the default float32 precision
+    attn_implementation="sdpa",
     device_map="auto",
 )
     padding=True,
 )
+# Remove token_type_ids: HF uses it to enable bidirectional attention for image tokens; molmoweb is trained with causal attention only
+inputs = {k: v.to("cuda") for k, v in inputs.items() if k != "token_type_ids"}
 with torch.inference_mode():
     output = model.generate(**inputs, max_new_tokens=200)