Instructions to use cherryboi/gemma2b-it-dutch-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cherryboi/gemma2b-it-dutch-v1 with Transformers:

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

pipe = pipeline("text-generation", model="cherryboi/gemma2b-it-dutch-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cherryboi/gemma2b-it-dutch-v1")
model = AutoModelForCausalLM.from_pretrained("cherryboi/gemma2b-it-dutch-v1")
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 cherryboi/gemma2b-it-dutch-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cherryboi/gemma2b-it-dutch-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cherryboi/gemma2b-it-dutch-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cherryboi/gemma2b-it-dutch-v1

SGLang

How to use cherryboi/gemma2b-it-dutch-v1 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 "cherryboi/gemma2b-it-dutch-v1" \
    --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": "cherryboi/gemma2b-it-dutch-v1",
		"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 "cherryboi/gemma2b-it-dutch-v1" \
        --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": "cherryboi/gemma2b-it-dutch-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cherryboi/gemma2b-it-dutch-v1 with Docker Model Runner:
```
docker model run hf.co/cherryboi/gemma2b-it-dutch-v1
```

gemma2b-it-dutch-v1

Model description

Really shitty finetune of gemma-2b-it using BramVanroy/alpaca-cleaned-dutch.

Intended uses & limitations

Its finetuned on gemma-2b-it which is an english model. However because gemma has a large vocab size i thought it to be interessting to see if it could learn dutch.

Training and evaluation data

Trained on BramVanroy/alpaca-cleaned-dutch dataset. Therefore, commercial use of this model is forbidden. The model is intended for research purposes only.

Training procedure

Trained with QLoRA and merged before upload.

Training hyperparameters

idk anymore tbh (i think it has been trained on 400 steps)

Downloads last month: 3

Safetensors

Model size

3B params

Tensor type

F16

cherryboi
/

gemma2b-it-dutch-v1