Instructions to use aripos1/gorani-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aripos1/gorani-3B with Transformers:

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

pipe = pipeline("text-generation", model="aripos1/gorani-3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aripos1/gorani-3B")
model = AutoModelForCausalLM.from_pretrained("aripos1/gorani-3B")
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

vLLM

How to use aripos1/gorani-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aripos1/gorani-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aripos1/gorani-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aripos1/gorani-3B

SGLang

How to use aripos1/gorani-3B 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 "aripos1/gorani-3B" \
    --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": "aripos1/gorani-3B",
		"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 "aripos1/gorani-3B" \
        --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": "aripos1/gorani-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use aripos1/gorani-3B with Docker Model Runner:
```
docker model run hf.co/aripos1/gorani-3B
```

Gorani Model Card

소개 (Introduce)

이 모델은 번역을 위한 모델입니다. 한국 고유어의 정확한 번역을 생성하기 위해 한국어, 영어, 일본어의 언어 데이터를 혼합하여 unsloth/Llama-3.2-3B-Instruct-bnb-4bit을 학습시켜 생성된 gorani-1B 입니다.
gorani는 현재 한국어, 영어, 일본어만 번역을 지원합니다.

모델 정보

개발자: airpos1
모델 유형: llama를 기반으로 하는 3B 매개변수 모델인 gorani-3B
지원 언어: 한국어, 영어, 일본어
라이센스: llama

Training Hyperparameters

per_device_train_batch_size: 8
gradient_accumulation_steps: 1
warmup_steps: 5
learning_rate: 2e-4
fp16: not is_bfloat16_supported()
num_train_epochs: 3
weight_decay: 0.01
lr_scheduler_type: "linear"

학습 데이터

데이터셋 링크

학습 성능 비교

Training Results

Downloads last month: 6

Safetensors

Model size

3B params

Tensor type

F32

F16

Model tree for aripos1/gorani-3B

Base model

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

Quantized

unsloth/Llama-3.2-3B-Instruct-bnb-4bit

Quantized

(113)

this model

aripos1
/

gorani-3B