Instructions to use amitha/molmo-clip-b16-olmo3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amitha/molmo-clip-b16-olmo3 with Transformers:

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

pipe = pipeline("image-text-to-text", model="amitha/molmo-clip-b16-olmo3", 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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForImageTextToText
model = AutoModelForImageTextToText.from_pretrained("amitha/molmo-clip-b16-olmo3", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use amitha/molmo-clip-b16-olmo3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "amitha/molmo-clip-b16-olmo3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amitha/molmo-clip-b16-olmo3",
		"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/amitha/molmo-clip-b16-olmo3

SGLang

How to use amitha/molmo-clip-b16-olmo3 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 "amitha/molmo-clip-b16-olmo3" \
    --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": "amitha/molmo-clip-b16-olmo3",
		"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 "amitha/molmo-clip-b16-olmo3" \
        --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": "amitha/molmo-clip-b16-olmo3",
		"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 amitha/molmo-clip-b16-olmo3 with Docker Model Runner:
```
docker model run hf.co/amitha/molmo-clip-b16-olmo3
```

molmo-clip-b16-olmo3 / config.json

amitha

Upload folder using huggingface_hub

d2b31cd verified 4 months ago

Raw History Blame Contribute Delete

3.18 kB

	{
	"architectures": [
	"MolmoOlmo3ForConditionalGeneration"
	],
	"auto_map": {
	"AutoConfig": "configuration_molmo_olmo3.MolmoOlmo3Config",
	"AutoModelForImageTextToText": "modeling_molmo_olmo3.MolmoOlmo3ForConditionalGeneration",
	"AutoImageProcessor": "image_processing_molmo_olmo3.MolmoOlmo3ImageProcessor",
	"AutoProcessor": "processing_molmo_olmo3.MolmoOlmo3Processor"
	},
	"bos_token_id": 100257,
	"dtype": "float32",
	"eos_token_id": 100257,
	"image_col_token_id": 100281,
	"image_end_token_id": 100279,
	"image_prompt_token_id": 100282,
	"image_start_token_id": 100278,
	"image_token_id": 100280,
	"include_cls_token": true,
	"lm_head_vocab_size": 100352,
	"model_type": "molmo_olmo3",
	"projector_hidden_act": "silu",
	"projector_intermediate_size": 11008,
	"text_config": {
	"architectures": [
	"Olmo3ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"dtype": "bfloat16",
	"eos_token_id": 100257,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 11008,
	"layer_types": [
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention"
	],
	"max_position_embeddings": 65536,
	"model_type": "olmo3",
	"num_attention_heads": 32,
	"num_hidden_layers": 32,
	"num_key_value_heads": 32,
	"pad_token_id": 100277,
	"rms_norm_eps": 1e-06,
	"rope_scaling": {
	"attention_factor": 1.2079441541679836,
	"beta_fast": 32,
	"beta_slow": 1,
	"factor": 8.0,
	"original_max_position_embeddings": 8192,
	"rope_type": "yarn"
	},
	"rope_theta": 500000,
	"sliding_window": 4096,
	"use_cache": true,
	"vocab_size": 100480
	},
	"text_hidden_size": 4096,
	"tie_word_embeddings": false,
	"transformers_version": "4.57.1",
	"vision_config": {
	"attention_dropout": 0.0,
	"hidden_act": "gelu",
	"hidden_size": 768,
	"image_size": 224,
	"initializer_factor": 1.0,
	"initializer_range": 0.02,
	"intermediate_size": 3072,
	"layer_norm_eps": 1e-05,
	"model_type": "clip_vision_model",
	"num_attention_heads": 12,
	"num_channels": 3,
	"num_hidden_layers": 12,
	"patch_size": 16,
	"projection_dim": 512
	},
	"vision_feature_layer": -1,
	"vision_final_norm_attr": "norm",
	"vision_hidden_size": 768,
	"vision_strip_final_norm": false,
	"vision_tower_name_or_path": "amitha/clip-vit-b16-datacomp-medium",
	"vision_trust_remote_code": false
	}