metadata
license: llama3
language:
- ko
- en
library_name: transformers
pipeline_tag: text-generation
- Basemodel MLP-KTLim/llama-3-Korean-Bllossom-8B
- Dataset
Python code with Pipeline
import transformers
import torch
model_id = "VIRNECT/llama-3-Korean-8B-V3"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device_map="auto",
)
pipeline.model.eval()
PROMPT = '''๋น์ ์ ์ธ๊ฐ๊ณผ ๋ํํ๋ ์น์ ํ ์ฑ๋ด์
๋๋ค. ์ง๋ฌธ์ ๋ํ ์ ๋ณด๋ฅผ ์ํฉ์ ๋ง๊ฒ ์์ธํ ์ ๊ณตํฉ๋๋ค. ๋น์ ์ด ์ง๋ฌธ์ ๋ํ ๋ต์ ๋ชจ๋ฅธ๋ค๋ฉด, ์ฌ์ค์ ๋ชจ๋ฅธ๋ค๊ณ ๋งํฉ๋๋ค.'''
instruction = "๋ณต์ก๋ ์ด๋ก ์์ PH๋ ๋ฌด์์ธ๊ฐ์?"
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):])