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
```

Patch for Model Card Example - Expected all tensors to be on the same device

by preoccupy9217 - opened May 20, 2025

Discussion

preoccupy9217

May 20, 2025

Running the example listed on the Model Card generated the following errors:

/home/aac/projects/granite-4-tf-rocm/venv/lib/python3.12/site-packages/transformers/generation/utils.py:2479: UserWarning: You are calling .generate() with the `input_ids` being on a device type different than your model's device. `input_ids` is on cuda, whereas the model is on cpu. You may experience unexpected behaviors or slower generation. Please make sure that you have put `input_ids` to the correct device by calling for example input_ids = input_ids.to('cpu') before running `.generate()`. 

...

RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument index in method wrapper_CUDA__index_select)

The following patch resolved the error by appending ".to(device)" when creating model:

10c10
<     )
---
>     ).to(device)

Test system was Ubuntu 24.04.2 LTS, ROCm 6.4.0, with 2x AMD EPYC 7763 64-Core Processors and 1x AMD Instinct MI210 using pip3 install transformers[torch]@git+https://github.com/huggingface/transformers as of May 20, 2025.

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