๐ค hyperclovax-sft-1.5b-v1
HyperCLOVAX-SEED-Text-Instruct-1.5B ๋ชจ๋ธ์ ๊ธฐ๋ฐ์ผ๋ก, LoRA ๋ฐฉ์์ Instruction tuning์ ์ ์ฉํ ํ๊ตญ์ด ์ธ์ด๋ชจ๋ธ์ ๋๋ค.
์ด ๋ชจ๋ธ์ ๋ค์๊ณผ ๊ฐ์ ์กฐ๊ฑด์์ ํ์ต๋์์ต๋๋ค:
- Base model:
naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-1.5B
- Tuning method: PEFT (LoRA), SFTTrainer
- ์ฌ์ฉ ์์: ๋ฌธ์ ๊ธฐ๋ฐ ์ง๋ฌธ ์๋ต, ํ๋ก์ ํธ ์๊ฐ ์์ฝ, ๊ฐ๊ฒฐํ ๋๋ต ์์ฑ ๋ฑ
๐ง ์ฌ์ฉ๋ฒ
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
# ํ ํฌ๋์ด์ ๋ก๋
tokenizer = AutoTokenizer.from_pretrained("sunnyanna/hyperclovax-sft-1.5b-v1")
# base + LoRA merge
base_model = AutoModelForCausalLM.from_pretrained(
"naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-1.5B"
)
model = PeftModel.from_pretrained(base_model, "sunnyanna/hyperclovax-sft-1.5b-v1")
model = model.merge_and_unload()
model.eval()
# Model Card for hyperclovax_sft_results
This model is a fine-tuned version of [naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-1.5B](https://huggingface.co/naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-1.5B).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="None", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
์์
๋ฌธ์๋ฅผ ์ฝ๊ณ ์๋ ์ง๋ฌธ์ ๋ตํ์ธ์.
### Input:
๋ฌธ์:
Pumati๋ ์นด์นด์คํ
ํฌ ๋ถํธ์บ ํ ๊ต์ก์๋ค์ ์ํ ํธ๋ํฝ ํ์์ด ํ๋ซํผ์
๋๋ค.
์ฌ์ฉ์๊ฐ ๋ค๋ฅธ ํ ํ๋ก์ ํธ๋ฅผ ์ง์ ์ฌ์ฉํ๊ณ ๋ฆฌ๋ทฐํ๋ฉด ์ฐ๋ฆฌ ํ์ ๋
ธ์ถ ์์๊ฐ ์ฌ๋ผ๊ฐ๋ ๊ตฌ์กฐ์
๋๋ค.
์ง๋ฌธ: ์ด๊ฑด ์ด๋ค ํ๋ก์ ํธ์ผ?
### Output:
Pumati๋ ์๋ก์ ํ๋ก์ ํธ๋ฅผ ์ฒดํํ๊ณ ์์ํ๋ฉฐ, ํธ๋ํฝ์ ๊ณต์ ํ ์ ์๋๋ก ์ค๊ณ๋ ๊ต์ก์ ๊ฐ์ ์ปค๋ฎค๋ํฐ ๊ธฐ๋ฐ ํ๋ซํผ์
๋๋ค.
Training procedure
This model was trained with SFT.
Framework versions
- PEFT 0.15.2
- TRL: 0.19.0
- Transformers: 4.52.4
- Pytorch: 2.6.0+cu124
- Datasets: 3.6.0
- Tokenizers: 0.21.2
Citations
Cite TRL as:
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
- Downloads last month
- 11
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support