- Basemodel MLP-KTLim/llama-3-Korean-Bllossom-8B
- Dataset AI Hub - ํ๊ตญ์ด ์ฑ๋ฅ์ด ๊ฐ์ ๋ ์ด๊ฑฐ๋AI ์ธ์ด๋ชจ๋ธ ๊ฐ๋ฐ ๋ฐ ๋ฐ์ดํฐ
Python code with Pipeline
import transformers
import torch
model_id = "VIRNECT/llama-3-Korean-8B-r-v2"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device_map="auto",
)
pipeline.model.eval()
PROMPT = '''You are a helpful AI assistant. Please answer the user's questions kindly. ๋น์ ์ ์ ๋ฅํ AI ์ด์์คํดํธ ์
๋๋ค. ์ฌ์ฉ์์ ์ง๋ฌธ์ ๋ํด ์น์ ํ๊ฒ ๋ต๋ณํด์ฃผ์ธ์.'''
instruction = "ํํ๊ณตํ์ด ๋ค๋ฅธ ๊ณตํ ๋ถ์ผ์ ์ด๋ป๊ฒ ๋ค๋ฅธ๊ฐ์?"
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):])
- Downloads last month
- 1,542
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.