gpt3-kor-based_gpt2_review_SR2

ehdwns1516/gpt3-kor-based_gpt2_review_SR2

• This model has been trained Korean dataset as a star of 2 in the naver shopping reivew dataset.
• Input text what you want to generate review.
• If the context is longer than 1200 characters, the context may be cut in the middle and the result may not come out well.

review generator DEMO: Ainize DEMO

review generator API: Ainize API

Model links for each 1 to 5 star

• ehdwns1516/gpt3-kor-based_gpt2_review_SR1
• ehdwns1516/gpt3-kor-based_gpt2_review_SR2
• ehdwns1516/gpt3-kor-based_gpt2_review_SR3
• ehdwns1516/gpt3-kor-based_gpt2_review_SR4
• ehdwns1516/gpt3-kor-based_gpt2_review_SR5

Overview

Language model: gpt3-kor-small_based_on_gpt2

Language: Korean

Training data: review_body dataset with a star of 2 in the naver shopping reivew dataset.

Code: See Ainize Workspace

Usage

In Transformers

from transformers import AutoTokenizer, AutoModelWithLMHead
  
tokenizer = AutoTokenizer.from_pretrained("ehdwns1516/gpt3-kor-based_gpt2_review_SR2")

model = AutoModelWithLMHead.from_pretrained("ehdwns1516/gpt3-kor-based_gpt2_review_SR2")

generator = pipeline(
    "text-generation",
    model="ehdwns1516/gpt3-kor-based_gpt2_review_SR2",
    tokenizer=tokenizer
)

context = "your context"

result = dict()
result[0] = generator(context)[0]