t5-large-finetuned-multi_v2

This model is a fine-tuned version of paust/pko-t5-large on the None dataset.

Model description

의도	개체
일상대화
전화연결	대상
장소안내	장소, 대상
날씨예보	날짜, 장소, 대상, 시간, 조건
화물추천	날짜, 시간, 상차, 하차, 기준
긍부정	긍정, 부정, 중립
*대상 : 상차지/하차지

How to use

import requests
 
API_URL = "https://api-inference.huggingface.co/models/yeye776/t5-large-finetuned-multi_v2"
headers = {"Authorization": "Bearer hf_key"}

def query(payload):
    response = requests.post(API_URL, headers=headers, json=payload)
    return response.json()

prompt = "브로캐리에 관련된 이용자의 대화인데 분류 및 인식 해줘! :"
input = "내일 심야 상차지가 분당인 화물 추천해줘"

output = query({
    "inputs": prompt+input,
    "options":{"wait_for_model":True}
})

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0007
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.06
• num_epochs: 8

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1