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", 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=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
```

Hermes tool calling isn't working with Inkling-NVFP4

#14

by ssalvo41 - opened 16 days ago

Discussion

ssalvo41

16 days ago

When using thinkingmachines/Inkling-NVFP4 with Hermes Agent, the model sometimes outputs the raw tool call instead of returning a normal assistant response or triggering the tool.
Example:

<|content_invoke_tool_json|>{"name":"terminal","args":{"command":"ls -la && echo '---' && find . -type f | head -30"}}<|end_message|>

Has anyone else experienced this? Is there a recommended chat template or inference configuration to make tool calling work correctly?

mrchuy

16 days ago

This got further as far as fixing the missing developer role and empty string https://gist.github.com/chuyqa/49c4d4f85b399e66de4a7e838cbf8504 but out of gpus for the week to test further

ssalvo41

14 days ago

•

edited 14 days ago

Still the same error

 <|content_invoke_tool_json|>{"name":"terminal","args":{"command":"cat ~/Desktop/multiagent-automatization/pyproject.toml"}}<|end_message|>

simon-thinky

Thinking Machines Lab org 1 day ago

@xzrderek for visibility

simon-thinky

Thinking Machines Lab org about 19 hours ago

Thanks for reporting this issue! We have taken that feedback and will try improve model's usability with hermes agent harness in the future!

simon-thinky changed discussion status to closed about 19 hours ago

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