Instructions to use ibm-granite/granite-4.2-30b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ibm-granite/granite-4.2-30b with Transformers:

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

pipe = pipeline("text-generation", model="ibm-granite/granite-4.2-30b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ibm-granite/granite-4.2-30b")
model = AutoModelForCausalLM.from_pretrained("ibm-granite/granite-4.2-30b", device_map="auto")
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]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ibm-granite/granite-4.2-30b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ibm-granite/granite-4.2-30b"
# 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-4.2-30b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ibm-granite/granite-4.2-30b

SGLang

How to use ibm-granite/granite-4.2-30b 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-4.2-30b" \
    --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-4.2-30b",
		"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-4.2-30b" \
        --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-4.2-30b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ibm-granite/granite-4.2-30b with Docker Model Runner:
```
docker model run hf.co/ibm-granite/granite-4.2-30b
```

What if do_sample=False?

by ErrDivine - opened 5 days ago

Discussion

ErrDivine

5 days ago

The README warns that it's important to set the temperature and top_p as such. I wonder what will happen if I set do_sample=False and use greedy search, because in some research setting this is necessary, like controlling variables on generation.

Lounafa1

5 days ago

As far as i understand, do_sample=False will disable the random sampling from the output layer, so it will always select the output token that has the highest score. It will make outputs identical no matter what temperature or top_p parameters are

ErrDivine

5 days ago

Yeh, thanks for your kind help. But I think there's more lying underneath that warning. I guess maybe the performance will drop dramatically or the model generation is corrupted. Otherwise they don't have to put a warning that big.

Lounafa1

5 days ago

Yeah, the performance can drop. Also it might get stuck in a loop repeating the same words, this is why i think the warning is there

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