maywell/korean_textbooks
Viewer • Updated • 4.42M • 1.95k • 124
How to use Seonghaa/gpt-oss-korean-model with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="Seonghaa/gpt-oss-korean-model")
messages = [
{"role": "user", "content": "Who are you?"},
]
pipe(messages) # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Seonghaa/gpt-oss-korean-model")
model = AutoModelForCausalLM.from_pretrained("Seonghaa/gpt-oss-korean-model")
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]:]))How to use Seonghaa/gpt-oss-korean-model with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Seonghaa/gpt-oss-korean-model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "Seonghaa/gpt-oss-korean-model",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'docker model run hf.co/Seonghaa/gpt-oss-korean-model
How to use Seonghaa/gpt-oss-korean-model with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "Seonghaa/gpt-oss-korean-model" \
--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": "Seonghaa/gpt-oss-korean-model",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'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 "Seonghaa/gpt-oss-korean-model" \
--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": "Seonghaa/gpt-oss-korean-model",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'How to use Seonghaa/gpt-oss-korean-model with Unsloth Studio:
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 Seonghaa/gpt-oss-korean-model to start chatting
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 Seonghaa/gpt-oss-korean-model to start chatting
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Seonghaa/gpt-oss-korean-model to start chatting
pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
model_name="Seonghaa/gpt-oss-korean-model",
max_seq_length=2048,
)How to use Seonghaa/gpt-oss-korean-model with Docker Model Runner:
docker model run hf.co/Seonghaa/gpt-oss-korean-model
이 모델은 unsloth/gpt-oss-20b를 기반으로 maywell/korean_textbooks 데이터셋으로 파인튜닝된 한국어 교육 전용 모델입니다. LoRA(Low-Rank Adaptation)로 학습 후, 베이스 모델에 병합하여 단일 모델로 배포됩니다.
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model = AutoModelForCausalLM.from_pretrained(
"Seonghaa/gpt-oss-korean-model",
torch_dtype=torch.float16,
device_map="auto",
trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("Seonghaa/gpt-oss-korean-model", trust_remote_code=True)
messages = [
{"role": "system", "content": "당신은 한국어로 교육 내용을 설명하는 도움이 되는 어시스턴트입니다."},
{"role": "user", "content": "2의 거듭제곱에 대해 설명해주세요."}
]
inputs = tokenizer.apply_chat_template(
messages, add_generation_prompt=True, return_tensors="pt"
).to(model.device)
outputs = model.generate(
**inputs, max_new_tokens=512, temperature=0.7, top_p=0.9,
pad_token_id=tokenizer.eos_token_id
)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))