Input Models input text only.
Output Models generate text only.
Base Model beomi/Yi-Ko-6B
Training Dataset
Implementation Code
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
repo = "ifuseok/yi-ko-playtus-instruct-v0.2"
OpenOrca = AutoModelForCausalLM.from_pretrained(
repo,
return_dict=True,
torch_dtype=torch.float16,
device_map='auto'
)
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)
Prompt Example
<|system|>
시스템 메시지 입니다. <|endoftext|>
<|user|>
유저 입니다.<|endoftext|>
<|assistant|>
어시스턴트 입니다.<|endoftext|>