sharaddition/paraphrase-gpt 🔢📝 → 📝

▶️ 4.3K runs 📅 May 2023 ⚙️ Cog 0.7.1 🔗 GitHub
paraphrasing text-generation text-paraphrasing

About

T5 model fine tuned on GPT-3.5 generated paraphrase corpus of 6.3 million unique sentences.

Example Output

Prompt:

"These practices, also known as ‘dark patterns,’ are in the nature of unfair trade practices and are covered under the Consumer Protection Act, which is punishable, according to Union consumer affairs secretary Rohit Kumar Singh."

Output

According to Rohit Kumar Singh, the Union consumer affairs secretary, 'dark patterns' are unfair trade practices that fall under the Consumer Protection Act and can be punished.Rohit Kumar Singh, the Union consumer affairs secretary, has stated that 'dark patterns' are unfair trade practices and fall under the Consumer Protection Act, which is punishable by law.The 'dark patterns' are unfair trade practices that fall under the scope of the Consumer Protection Act and can be punished, as stated by Union consumer affairs secretary Rohit Kumar Singh.Union consumer affairs secretary Rohit Kumar Singh has stated that 'dark patterns' are unfair trade practices, which fall under the scope of the Consumer Protection Act and can be punished.'Dark patterns,’ also known as unfair trade practices, are covered by the Consumer Protection Act and can result in punishment, according to Union consumer affairs secretary Rohit Kumar Singh.

Performance Metrics

2.37s Prediction Time
2.54s Total Time
All Input Parameters 
{
  "top_p": 1,
  "prompt": "These practices, also known as ‘dark patterns,’ are in the nature of unfair trade practices and are covered under the Consumer Protection Act, which is punishable, according to Union consumer affairs secretary Rohit Kumar Singh.",
  "num_beams": 5,
  "max_length": 250,
  "temperature": 0.75,
  "num_beam_groups": 5,
  "diversity_penalty": 3,
  "repetition_penalty": 10,
  "no_repeat_ngram_size": 2,
  "num_return_sequences": 5
}
Input Parameters
top_p Type: numberDefault: 1Range: 0.01 - 1
When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens
prompt (required) Type: string
Prompt to send to FLAN-T5.
num_beams Type: integerDefault: 5Range: 1 - 5
Number of output sequences to generate
max_length Type: integerDefault: 50Range: 1 - ∞
Maximum number of tokens to generate. A word is generally 2-3 tokens
temperature Type: numberDefault: 0.75Range: 0.01 - 5
Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.
num_beam_groups Type: integerDefault: 5Range: 1 - 5
Number of output sequences to generate
diversity_penalty Type: numberDefault: 3Range: 0.01 - 5
Penalty for repeated words in generated text; 1 is no penalty, values greater than 1 discourage repetition, less than 1 encourage it.
repetition_penalty Type: numberDefault: 10Range: 0.01 - 15
Penalty for repeated words in generated text; 1 is no penalty, values greater than 1 discourage repetition, less than 1 encourage it.
no_repeat_ngram_size Type: integerDefault: 2Range: 0.01 - 5
No repeat n_gram size.
num_return_sequences Type: integerDefault: 5Range: 1 - 5
Number of output sequences to generate
Output Schema

Output

Type: array • Items Type: string

Version Details
Version ID
3a66bc6c1327de5459cb18b2f10550693bc69662a5e29c67a971776f8574f1b1
Version Created
May 13, 2023
Run on Replicate →