Instructions to use Lauarvik/granite-4.1-8b-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lauarvik/granite-4.1-8b-heretic with Transformers:

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

pipe = pipeline("text-generation", model="Lauarvik/granite-4.1-8b-heretic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Lauarvik/granite-4.1-8b-heretic")
model = AutoModelForCausalLM.from_pretrained("Lauarvik/granite-4.1-8b-heretic")
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 Settings

vLLM

How to use Lauarvik/granite-4.1-8b-heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Lauarvik/granite-4.1-8b-heretic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lauarvik/granite-4.1-8b-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Lauarvik/granite-4.1-8b-heretic

SGLang

How to use Lauarvik/granite-4.1-8b-heretic 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 "Lauarvik/granite-4.1-8b-heretic" \
    --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": "Lauarvik/granite-4.1-8b-heretic",
		"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 "Lauarvik/granite-4.1-8b-heretic" \
        --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": "Lauarvik/granite-4.1-8b-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Lauarvik/granite-4.1-8b-heretic with Docker Model Runner:
```
docker model run hf.co/Lauarvik/granite-4.1-8b-heretic
```

granite-4.1-8b-heretic / reproduce /README.md

Lauarvik

Upload reproduce/README.md with huggingface_hub

4a86f78 verified 2 months ago

preview code

Raw

History Blame Contribute Delete

4.17 kB

Reproduction guide

This directory contains the necessary information and assets to reproduce the results obtained during this Heretic run.

Git installation

This system installed Heretic from a Git repository: https://github.com/p-e-w/heretic.git @ ebb5e651df4be58d05cb4f28652e65d725e845eb

To reproduce the model, you must install Heretic from this exact repository and commit.

Models

Base model: ibm-granite/granite-4.1-8b (Commit: 7bb65b7)

Datasets

Good prompts: mlabonne/harmless_alpaca (Commit: 02c6a92)
Bad prompts: mlabonne/harmful_behaviors (Commit: 01cead0)
Good evaluation prompts: mlabonne/harmless_alpaca (Commit: 02c6a92)
Bad evaluation prompts: mlabonne/harmful_behaviors (Commit: 01cead0)

Selected trial

Trial number: 7
KL divergence: 0.064686
Refusals: 1/100

System

Python: 3.12.12 (CPython, GCC 11.4.0) [System]
Operating system: Linux-6.6.113+-x86_64-with-glibc2.35 (x86_64)
CPU: Intel(R) Xeon(R) CPU @ 2.00GHz

Accelerators

CUDA: Detected 2 device(s) (29.12 GB total VRAM)
- CUDA Version: 12.8
- Driver Version: 580.105.08
Devices:
- CUDA 0: Tesla T4 (14.56 GB)
- CUDA 1: Tesla T4 (14.56 GB)

Environment

Heretic: v1.2.0 (Origin: Git (https://github.com/p-e-w/heretic.git @ ebb5e651df4be58d05cb4f28652e65d725e845eb))
PyTorch: 2.10.0+cu128
Other dependencies: See requirements.txt.

Contents of this directory

requirements.txt: The exact versions of all Python packages.
config.toml: The exact configuration used, including the RNG seed.
ibm-granite--granite-4--1-8b.jsonl: The Optuna study journal containing the history of all trials.
SHA256SUMS: Cryptographic hashes for all weight files.
reproduce.json: A machine-readable file containing all reproducibility information.

How to reproduce

Ensure your system matches the specifications in the System section above. Exact reproducibility is only guaranteed if all aspects of your system are identical to the one the model was originally generated on.
Install the exact version of Heretic indicated in the Environment section above, from its original source.
Install the packages listed in requirements.txt: pip install -r requirements.txt
Install the correct version of PyTorch: pip install torch==2.10.0+cu128 --index-url https://download.pytorch.org/whl/cu128
Place the provided config.toml in your working directory.
Run Heretic without any additional arguments: heretic
Wait for the run to finish, then select trial 7 and export the model.
Verify that the weight files have been exactly reproduced by comparing their SHA-256 hashes against those in SHA256SUMS: sha256sum -c SHA256SUMS (or look at the hashes online if you uploaded to Hugging Face)

To use the included Optuna study journal ibm-granite--granite-4--1-8b.jsonl, place it in the checkpoints directory (usually checkpoints/) before running Heretic.

This allows you to export other models from the Pareto front, or to run additional trials without having to re-run the stored trials.