Instructions to use shiningdota/Llama-3.2-3B_Instruct_Indonesian with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shiningdota/Llama-3.2-3B_Instruct_Indonesian with Transformers:

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

pipe = pipeline("text-generation", model="shiningdota/Llama-3.2-3B_Instruct_Indonesian")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("shiningdota/Llama-3.2-3B_Instruct_Indonesian")
model = AutoModelForCausalLM.from_pretrained("shiningdota/Llama-3.2-3B_Instruct_Indonesian")
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 shiningdota/Llama-3.2-3B_Instruct_Indonesian with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shiningdota/Llama-3.2-3B_Instruct_Indonesian"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shiningdota/Llama-3.2-3B_Instruct_Indonesian",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/shiningdota/Llama-3.2-3B_Instruct_Indonesian

SGLang

How to use shiningdota/Llama-3.2-3B_Instruct_Indonesian 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 "shiningdota/Llama-3.2-3B_Instruct_Indonesian" \
    --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": "shiningdota/Llama-3.2-3B_Instruct_Indonesian",
		"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 "shiningdota/Llama-3.2-3B_Instruct_Indonesian" \
        --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": "shiningdota/Llama-3.2-3B_Instruct_Indonesian",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use shiningdota/Llama-3.2-3B_Instruct_Indonesian 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 shiningdota/Llama-3.2-3B_Instruct_Indonesian 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 shiningdota/Llama-3.2-3B_Instruct_Indonesian to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for shiningdota/Llama-3.2-3B_Instruct_Indonesian to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="shiningdota/Llama-3.2-3B_Instruct_Indonesian",
    max_seq_length=2048,
)

Docker Model Runner
How to use shiningdota/Llama-3.2-3B_Instruct_Indonesian with Docker Model Runner:
```
docker model run hf.co/shiningdota/Llama-3.2-3B_Instruct_Indonesian
```

Model Details

Finetuned Llama-3.2-3B with MBZUAI-Bactrian-X Indonesian datasets only

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Model Example Results

### Instruksi:
Berikan empat tips agar tetap sehat.

### Masukan:


### Tanggapan:
1. Berolahraga secara teratur: Olahraga membantu meningkatkan kesehatan fisik dan mental. Olahraga yang dilakukan secara teratur dapat membantu meningkatkan kesehatan jantung, mengurangi berat badan, meningkatkan kekuatan otot, dan meningkatkan kesehatan tulang.

2. Makan makanan sehat: Makanan yang sehat dapat membantu menjaga kesehatan tubuh. Makanan yang kaya akan vitamin, mineral, dan protein dapat membantu menjaga kesehatan tubuh dan memperbaiki kesehatan yang ada.

3. Tidur yang cukup: Tidur yang cukup sangat penting untuk menjaga kesehatan tubuh. Tidur yang cukup dapat membantu meningkatkan kesehatan tubuh, meningkatkan konsentrasi, dan membantu mengurangi stres.

4. Hindari kebiasaan buruk: Kebiasaan buruk seperti merokok, minum alkohol, dan mengonsumsi makanan yang tidak sehat dapat membahayakan kesehatan tubuh. Hindari kebiasaan buruk ini dan ganti dengan kebiasaan yang sehat dan positif.<|eot_id|>

Downloads last month: 1

Safetensors

Model size

3B params

Tensor type

F16

Model tree for shiningdota/Llama-3.2-3B_Instruct_Indonesian

Base model

meta-llama/Llama-3.2-3B-Instruct

Finetuned

(1608)

this model

shiningdota
/

Llama-3.2-3B_Instruct_Indonesian

Model Details

Model Example Results

Model tree for shiningdota/Llama-3.2-3B_Instruct_Indonesian

Dataset used to train shiningdota/Llama-3.2-3B_Instruct_Indonesian