Instructions to use allenai/Molmo2-ER with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use allenai/Molmo2-ER with Transformers:

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

pipe = pipeline("image-text-to-text", model="allenai/Molmo2-ER", 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/Molmo2-ER", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use allenai/Molmo2-ER with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "allenai/Molmo2-ER"
# 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/Molmo2-ER",
		"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/Molmo2-ER

SGLang

How to use allenai/Molmo2-ER 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/Molmo2-ER" \
    --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/Molmo2-ER",
		"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/Molmo2-ER" \
        --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/Molmo2-ER",
		"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/Molmo2-ER with Docker Model Runner:
```
docker model run hf.co/allenai/Molmo2-ER
```

weikaih commited on 23 days ago

Commit

a0b1e4b

verified ·

1 Parent(s): 413c18f

Replace bf16 weights with fp32

Browse files

Files changed (6) hide show

config.json +1 -1
model-00001-of-00002.safetensors → model-00001-of-00004.safetensors +2 -2
model-00002-of-00002.safetensors → model-00002-of-00004.safetensors +2 -2
model-00003-of-00004.safetensors +3 -0
model-00004-of-00004.safetensors +3 -0
model.safetensors.index.json +0 -0

config.json CHANGED Viewed

@@ -27,7 +27,7 @@
     "AutoConfig": "configuration_molmo2.Molmo2Config",
     "AutoModelForImageTextToText": "modeling_molmo2.Molmo2ForConditionalGeneration"
   },
-  "dtype": "bfloat16",
   "frame_end_token_id": 151944,
   "frame_start_token_id": 151943,
   "image_col_id": 151939,

     "AutoConfig": "configuration_molmo2.Molmo2Config",
     "AutoModelForImageTextToText": "modeling_molmo2.Molmo2ForConditionalGeneration"
   },
+  "dtype": "float32",
   "frame_end_token_id": 151944,
   "frame_start_token_id": 151943,
   "image_col_id": 151939,

model-00001-of-00002.safetensors → model-00001-of-00004.safetensors RENAMED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:972d989cac0fff4f7c06f787266a135e0a0fcedd59219f904af44fa65e2b9d02
-size 4967870232

 version https://git-lfs.github.com/spec/v1
+oid sha256:12921633f1ff67db04516fdd37160a5b88057c1611acefb74117ea0f5dcb5773
+size 4891799000

model-00002-of-00002.safetensors → model-00002-of-00004.safetensors RENAMED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41f8a4ed95b156376f78d4fffda544f2c108b2b9b1ddc85cff8a44414d5f37af
-size 4733966472

 version https://git-lfs.github.com/spec/v1
+oid sha256:fb09af13aaf7a5630e7d6ecec06df670494302797d46f1ba6dacae7b7b1443fe
+size 4844690992

model-00003-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1601349698c99636e1f6e09a0b96b1da5a891c3b7f0ab72bc6590fdf39ce7ca4
+size 4844691024

model-00004-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:30481c43be906da15fb0d8f71b9708dd19582b380699e314323d7257014c7523
+size 4822393416

model.safetensors.index.json CHANGED Viewed

The diff for this file is too large to render. See raw diff