Instructions to use timothydillan/gemma4-e2b-balinese-cpt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use timothydillan/gemma4-e2b-balinese-cpt with Transformers:

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

pipe = pipeline("text-generation", model="timothydillan/gemma4-e2b-balinese-cpt")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("timothydillan/gemma4-e2b-balinese-cpt")
model = AutoModelForMultimodalLM.from_pretrained("timothydillan/gemma4-e2b-balinese-cpt")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use timothydillan/gemma4-e2b-balinese-cpt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "timothydillan/gemma4-e2b-balinese-cpt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "timothydillan/gemma4-e2b-balinese-cpt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/timothydillan/gemma4-e2b-balinese-cpt

SGLang

How to use timothydillan/gemma4-e2b-balinese-cpt 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 "timothydillan/gemma4-e2b-balinese-cpt" \
    --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": "timothydillan/gemma4-e2b-balinese-cpt",
		"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 "timothydillan/gemma4-e2b-balinese-cpt" \
        --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": "timothydillan/gemma4-e2b-balinese-cpt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use timothydillan/gemma4-e2b-balinese-cpt with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for timothydillan/gemma4-e2b-balinese-cpt to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for timothydillan/gemma4-e2b-balinese-cpt to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for timothydillan/gemma4-e2b-balinese-cpt to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="timothydillan/gemma4-e2b-balinese-cpt",
    max_seq_length=2048,
)

Docker Model Runner
How to use timothydillan/gemma4-e2b-balinese-cpt with Docker Model Runner:
```
docker model run hf.co/timothydillan/gemma4-e2b-balinese-cpt
```

Gemma-4-E2B — Balinese Continued Pretraining (CPT)

Stage 1 of the Open Indonesia Models Balinese assistant: continued pretraining of google/gemma-4-E2B-it on a Balinese text corpus (~25M tokens) to build Balinese fluency before instruction-tuning.

This is a base/fluency model, not an instruction-following assistant. The instruction-tuned assistant is a LoRA adapter trained on top of this model (oim-balinese-assistant-sft), served as this model + that adapter.

merged-16bit weights (load directly with transformers / Unsloth).
*-lora/ LoRA adapter from the CPT run is included for reference.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
m = AutoModelForCausalLM.from_pretrained("timothydillan/gemma4-e2b-balinese-cpt")
t = AutoTokenizer.from_pretrained("timothydillan/gemma4-e2b-balinese-cpt")