Instructions to use ibm-granite/granite-4.0-tiny-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ibm-granite/granite-4.0-tiny-preview with Transformers:

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

pipe = pipeline("text-generation", model="ibm-granite/granite-4.0-tiny-preview")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ibm-granite/granite-4.0-tiny-preview")
model = AutoModelForCausalLM.from_pretrained("ibm-granite/granite-4.0-tiny-preview")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ibm-granite/granite-4.0-tiny-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ibm-granite/granite-4.0-tiny-preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ibm-granite/granite-4.0-tiny-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ibm-granite/granite-4.0-tiny-preview

SGLang

How to use ibm-granite/granite-4.0-tiny-preview 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 "ibm-granite/granite-4.0-tiny-preview" \
    --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": "ibm-granite/granite-4.0-tiny-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "ibm-granite/granite-4.0-tiny-preview" \
        --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": "ibm-granite/granite-4.0-tiny-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ibm-granite/granite-4.0-tiny-preview with Docker Model Runner:
```
docker model run hf.co/ibm-granite/granite-4.0-tiny-preview
```

Suggestion: publishing (parts of the) training data

by FlipTip - opened May 8, 2025

Discussion

FlipTip

May 8, 2025

Hi IBM Team,
Thanks for the permissive license.

Are there any plans to release the training data, or parts of it, to help the community gain deeper insights into the model? Alternatively, sharing the synthetic data generation pipeline would also go a long way towards better understanding.

Community-driven open-source AI thrives on transparency; it accelerates collaborative research.

Thanks again for your contributions to the AI research community.

gabegoodhart

IBM Granite org May 8, 2025

Hi @FlipTip , thanks for bringing up the topic of data transparency. A detailed description of the training data will be released in the final whitepaper when the full set of 4.0 models is launched, so stay tuned!

TeetoTa

Jul 19, 2025

At least a calibration dataset for activation aware quantisation would be a blessing.

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