Instructions to use tostideluxekaas/GEITje-7b-ultra-Heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tostideluxekaas/GEITje-7b-ultra-Heretic with Transformers:

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

pipe = pipeline("text-generation", model="tostideluxekaas/GEITje-7b-ultra-Heretic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tostideluxekaas/GEITje-7b-ultra-Heretic")
model = AutoModelForCausalLM.from_pretrained("tostideluxekaas/GEITje-7b-ultra-Heretic", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tostideluxekaas/GEITje-7b-ultra-Heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tostideluxekaas/GEITje-7b-ultra-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": "tostideluxekaas/GEITje-7b-ultra-Heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tostideluxekaas/GEITje-7b-ultra-Heretic

SGLang

How to use tostideluxekaas/GEITje-7b-ultra-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 "tostideluxekaas/GEITje-7b-ultra-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": "tostideluxekaas/GEITje-7b-ultra-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 "tostideluxekaas/GEITje-7b-ultra-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": "tostideluxekaas/GEITje-7b-ultra-Heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tostideluxekaas/GEITje-7b-ultra-Heretic with Docker Model Runner:
```
docker model run hf.co/tostideluxekaas/GEITje-7b-ultra-Heretic
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

GEItje Heretic (pre-uncensored)

This is an abbliterated version of GEITje-7b-ultra by BramVanRoy. It is abbliterated using the heretic lib and was used before the uncensoring fine-tune off tostideluxekaas/GEItje-7b-uncensored and tostideluxekaas/GEITje-7b-uncensored-GUFF. Performance on English is 4/100 but may vary in dutch. Which is why I chose to further fine-tune it.

Disclaimer

This model is provided as-is and may generate content that some users may find offensive, disturbing, or explicit. It is not intended for minors.

Use of this model is at your own risk. You are solely responsible for any outputs and for any decisions made or actions taken based on those outputs. The authors and maintainers disclaim all warranties and liability to the maximum extent permitted by law.

This model is intended for professional, research, educational, creative, and hobbyist use (preferably in local/offline environments) and is not intended for illegal or harmful purposes.