Instructions to use TeunS/Geert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TeunS/Geert with Transformers:

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

pipe = pipeline("text-generation", model="TeunS/Geert")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TeunS/Geert")
model = AutoModelForCausalLM.from_pretrained("TeunS/Geert", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

MLX

How to use TeunS/Geert with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("TeunS/Geert")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use TeunS/Geert with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TeunS/Geert:F16
# Run inference directly in the terminal:
llama cli -hf TeunS/Geert:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TeunS/Geert:F16
# Run inference directly in the terminal:
llama cli -hf TeunS/Geert:F16

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf TeunS/Geert:F16
# Run inference directly in the terminal:
./build/bin/llama cli -hf TeunS/Geert:F16

Use Docker

docker model run hf.co/TeunS/Geert:F16

Llama new
LM Studio
Jan

vLLM

How to use TeunS/Geert with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/TeunS/Geert:F16

SGLang

How to use TeunS/Geert 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 "TeunS/Geert" \
    --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": "TeunS/Geert",
		"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 "TeunS/Geert" \
        --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": "TeunS/Geert",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use TeunS/Geert with Ollama:
```
ollama run hf.co/TeunS/Geert:F16
```
Unsloth Desktop

MLX LM

How to use TeunS/Geert with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "TeunS/Geert"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "TeunS/Geert"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "TeunS/Geert",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use TeunS/Geert with Docker Model Runner:
```
docker model run hf.co/TeunS/Geert:F16
```

Lemonade

How to use TeunS/Geert with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TeunS/Geert:F16

Run and chat with the model

lemonade run user.Geert-F16

List all available models

lemonade list

Atomic Chat

TeunS/Geert

The Model TeunS/Geert was converted to MLX format from unsloth/gemma-2-2b-it using mlx-lm version 0.19.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("TeunS/Geert")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

Downloads last month: 55

Safetensors

Model size

3B params

Tensor type

BF16

MLX

Hardware compatibility

Quantized

Model tree for TeunS/Geert

Base model

unsloth/gemma-2-2b-it

Quantized

(12)

this model