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

Libraries

How to use thinkingmachines/Inkling with Transformers:

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

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

processor = AutoProcessor.from_pretrained("thinkingmachines/Inkling")
model = AutoModelForMultimodalLM.from_pretrained("thinkingmachines/Inkling")
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=40)
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 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thinkingmachines/Inkling"
# 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",
		"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

SGLang

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

Inkling / .gitattributes

aurick

Model release

91b051f 1 day ago

Raw

History Blame Contribute Delete

7.62 kB

	model-00050-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00014-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00082-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00044-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00052-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00011-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00047-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00070-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00099-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00040-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00029-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00043-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00019-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00012-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00084-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00101-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00093-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00090-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00054-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00035-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00005-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00030-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	tokenizer.json filter=lfs diff=lfs merge=lfs -text
	model-00007-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00071-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00021-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00003-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00018-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00026-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00034-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00069-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00008-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00059-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00013-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00104-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00038-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	mtp.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00049-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00028-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00027-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00015-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00105-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00048-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00087-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00085-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00017-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00046-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00020-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00051-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00079-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00057-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00036-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00081-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00100-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00097-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00010-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00080-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00032-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00061-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00074-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00060-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00066-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00102-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00095-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00041-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00078-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00083-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00006-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00058-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00045-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00067-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00072-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00103-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00024-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00031-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00096-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00023-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00092-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00076-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00063-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00107-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00098-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00001-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00089-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00009-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00106-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00075-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00025-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00077-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00108-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00086-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00065-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00004-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00039-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00062-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00094-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00068-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00091-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00022-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00088-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00016-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00073-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00033-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00064-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00056-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00037-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00053-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00042-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00002-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	model-00055-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
	tiktoken/tokenizer.model filter=lfs diff=lfs merge=lfs -text