Jin0's picture
Update README.md
a4561b1 verified
---
license: llama3
language:
- ko
- en
library_name: transformers
pipeline_tag: text-generation
---
- Basemodel [MLP-KTLim/llama-3-Korean-Bllossom-8B](https://huggingface.co/MLP-KTLim/llama-3-Korean-Bllossom-8B)
- Dataset
- [AI Hub - ํ•œ๊ตญ์–ด ์„ฑ๋Šฅ์ด ๊ฐœ์„ ๋œ ์ดˆ๊ฑฐ๋Œ€AI ์–ธ์–ด๋ชจ๋ธ ๊ฐœ๋ฐœ ๋ฐ ๋ฐ์ดํ„ฐ](https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=115&topMenu=100&dataSetSn=71748)
### Python code with Pipeline
```python
import transformers
import torch
model_id = "VIRNECT/llama-3-Korean-8B-V2"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device_map="auto",
)
pipeline.model.eval()
PROMPT = '''๋‹น์‹ ์€ ์ธ๊ฐ„๊ณผ ๋Œ€ํ™”ํ•˜๋Š” ์นœ์ ˆํ•œ ์ฑ—๋ด‡์ž…๋‹ˆ๋‹ค. ์งˆ๋ฌธ์— ๋Œ€ํ•œ ์ •๋ณด๋ฅผ ์ƒํ™ฉ์— ๋งž๊ฒŒ ์ž์„ธํžˆ ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค. ๋‹น์‹ ์ด ์งˆ๋ฌธ์— ๋Œ€ํ•œ ๋‹ต์„ ๋ชจ๋ฅธ๋‹ค๋ฉด, ์‚ฌ์‹ค์€ ๋ชจ๋ฅธ๋‹ค๊ณ  ๋งํ•ฉ๋‹ˆ๋‹ค.'''
instruction = "ํ™”ํ•™๊ณตํ•™์ด ๋‹ค๋ฅธ ๊ณตํ•™ ๋ถ„์•ผ์™€ ์–ด๋–ป๊ฒŒ ๋‹ค๋ฅธ๊ฐ€์š”?"
messages = [
{"role": "system", "content": f"{PROMPT}"},
{"role": "user", "content": f"{instruction}"}
]
prompt = pipeline.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = pipeline(
prompt,
max_new_tokens=2048,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9
)
print(outputs[0]["generated_text"][len(prompt):])
```