Prompt Shortener

Prompt Shortener

Shorten your prompts. You can recall your long prompts by simply typing a short code. You can also easily recall popular prompts created by others via shortcuts.

31 👀

Views

0 🌟

Ratings

Sign up to our newsletter

Get weekly updates on trending GPTs and new features.

More about this GPT 🌟

General Info 📄

Author: nnulu.com - Profile
Privacy Policy: Link
Last Updated: Jun 29, 2024
Share Recipient: marketplace
Tools used: plugins_prototype, browser, dalle, python

Additional Details

ID: 75472

Slug: prompt-shortener

Created At:

Updated At: Oct 28, 2024

Prompt Starters 💡

Welcome Message:
  • Shorten this prompt "I want to check the grammar of my paper. Correct grammar errors and polish the sentences. But do not correct abbreviations (e.g., Fig., vs.) and citations. The terms should be clear and scientific, and the corrected sentences should have high readability. Correct the following paragraph: (paper contents)"
  • Code: "jYHT". Paper: "The dominent sequence transduction models are based on complex recurrent or convolutional neural networks that includes an encoder and a decoder. The best performing models also connects the encoder and decoder through an attention mechanism. We proposes a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks shows these models to be superior in quality while being more parallelizable and requiring significant less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, include ensembles, by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training cost of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successful to English constituency parsing both with large and limited training data. "

Actions 🛠️

  • N/A - N/A
    Version: N/A
    Domain: api.nnulu.com