Instructions to use maywell/TinyWand-DPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use maywell/TinyWand-DPO with Transformers:

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

pipe = pipeline("text-generation", model="maywell/TinyWand-DPO")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("maywell/TinyWand-DPO")
model = AutoModelForMultimodalLM.from_pretrained("maywell/TinyWand-DPO")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use maywell/TinyWand-DPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "maywell/TinyWand-DPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "maywell/TinyWand-DPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/maywell/TinyWand-DPO

SGLang

How to use maywell/TinyWand-DPO 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 "maywell/TinyWand-DPO" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "maywell/TinyWand-DPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "maywell/TinyWand-DPO" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "maywell/TinyWand-DPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use maywell/TinyWand-DPO with Docker Model Runner:
```
docker model run hf.co/maywell/TinyWand-DPO
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

TinyWand-DPO

한국어 모델 설명

1.63B, 하찮은 크기의 SLM은 어떨까요?

모델 소개

TinyWand-DPO는 1.63B의 SLM 모델입니다. 이 모델은 1.63B라는 작은 크기를 가짐으로써 소형기기에서 구동되거나 큰 toks/s를 가질 수 있음과 동시에 강력한 성능을 보여줍니다.

모델 라이센스

OPEN

모델 성능

TBD

학습 과정

TBD

사용 안내

추론에 필요한 VRAM

양자화	입력 토큰 수	출력 토큰 수	메모리 사용량
bf16(base)	64	256	3,888 MiB
q4_K_M	64	256	1,788 MiB

프롬프트 템플릿

본 모델은 Alpaca 프롬프트 템플릿을 사용합니다.

해당 템플릿은 apply_chat_template()를 통해 허깅페이스 템플릿에서 확인 하실 수 있습니다.

아래 파이썬 코드를 사용하여 모델을 로드 및 사용 할 수 있습니다. transformers, torch가 사전 설치되어야함

from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda" # nvidia 그래픽카드 기준

tokenizer = AutoTokenizer.from_pretrained("maywell/TinyWand-DPO")
model = AutoModelForCausalLM.from_pretrained(
    "maywell/TinyWand-DPO",
    device_map="auto",
    torch_dtype=torch.bfloat16, # 사용하는 장비가 bfloat16을 지원하지 않는 경우 torch.float16으로 바꿔주세요.
)

messages = [
    {"role": "system", "content": "Below is an instruction that describes a task. Write a response that appropriately completes the request."}, # 비울 경우에도 동일하게 적용 됨.
    {"role": "user", "content": "언어모델의 파라미터 수가 작으면 어떤 이점이 있어?"},
]

encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")

model_inputs = encodeds.to(device)
model.to(device)

generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])

Downloads last month: 110

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for maywell/TinyWand-DPO

Quantizations

3 models