Downloads · 30 days
9
6% of all-time downloads
SkyOrbis/SKY-Ko-Qwen2.5-7B-Instruct-SFT-step-5000
SKY-Ko-Qwen2.5-7B-Instruct-SFT-step-5000 is a machine learning model from SkyOrbis. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
9
6% of all-time downloads
All-time downloads
152
Public
Parameters
7.6B
15.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors15.2 GB · 100%
From the Hugging Face model README
Training GPU: H100
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "SkyOrbis/SKY-Ko-Qwen2.5-7B-Instruct-SFT-step-10000"
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
prompt = "서울의 수도는?"
messages = [
{"role": "system", "content": "주어진 질문에 대답을 하세요."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
generated_ids = model.generate(
**model_inputs,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)