YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

개요

  • 한국어 요약 Task를 수행하는 모델입니다.

Base Model

Dataset

AI hub에 있는 아래 요약 데이터 중 3만건을 샘플링하여 사용하였습니다.

라이브러리 설치

pip3 install transformers gradio vllm

예제 코드

from vllm import LLM, SamplingParams
from transformers import AutoTokenizer
import gradio as gr
import os

model_path = "gangyeolkim/open-llama-2-ko-7b-summarization"
sampling_params = SamplingParams(max_tokens=1024, temperature=0.1)
tokenizer = AutoTokenizer.from_pretrained(model_path) 
 
llm = LLM(model=model_path, tokenizer=model_path, tensor_parallel_size=1) 

def gen(text, history):
    
    text = [
            "### 원문:",
            f"{text}\n",
            "### 요약:\n",
        ]

    prompts = "\n".join(text)
    outputs = llm.generate(prompts, sampling_params) 
    
    for output in outputs:
        generated_text = output.outputs[0].text
    return generated_text 
    
demo = gr.ChatInterface(gen)
demo.launch(share=True) 
Downloads last month
47
Safetensors
Model size
6.86B params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.