Instructions to use thinkingmachines/Inkling-2-Small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thinkingmachines/Inkling-2-Small with Transformers:

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

pipe = pipeline("image-text-to-text", model="thinkingmachines/Inkling-2-Small")
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 AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("thinkingmachines/Inkling-2-Small")
model = AutoModelForMultimodalLM.from_pretrained("thinkingmachines/Inkling-2-Small", 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 = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use thinkingmachines/Inkling-2-Small with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thinkingmachines/Inkling-2-Small"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thinkingmachines/Inkling-2-Small",
		"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/thinkingmachines/Inkling-2-Small

SGLang

How to use thinkingmachines/Inkling-2-Small 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 "thinkingmachines/Inkling-2-Small" \
    --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": "thinkingmachines/Inkling-2-Small",
		"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 "thinkingmachines/Inkling-2-Small" \
        --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": "thinkingmachines/Inkling-2-Small",
		"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 thinkingmachines/Inkling-2-Small with Docker Model Runner:
```
docker model run hf.co/thinkingmachines/Inkling-2-Small
```

Hopper cards not currently compatible with the vllm image.

by SuperbEmphasis - opened about 17 hours ago

Discussion

SuperbEmphasis

about 17 hours ago

  File "/usr/local/lib/python3.12/dist-packages/pydantic/_internal/_dataclasses.py", line 121, in __init__
    s.__pydantic_validator__.validate_python(ArgsKwargs(args, kwargs), self_instance=s)
pydantic_core._pydantic_core.ValidationError: 1 validation error for VllmConfig
  Value error, The quantization method inkling2 is not supported for the current GPU. Minimum capability: 100. Current capability: 90. [type=value_error, input_value=ArgsKwargs((), {'model_co... 'shutdown_timeout': 0}), input_type=ArgsKwargs]
    For further information visit https://errors.pydantic.dev/2.14/v/value_error

Hopefully support with hopper cards using the marlin kernel will come soon.

SuperbEmphasis

about 17 hours ago

To test, I tried the MXFP8 model as well, and received the same error.

I am running the container as specified:
vllm/vllm-openai:inkling-2-small

I also tried the latest nightly.

aurick

Thinking Machines Lab org about 15 hours ago

Hi @SuperbEmphasis , thanks for trying the model! Could you please open up an issue at https://github.com/vllm-project/vllm?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment