maraoz / Gpt Scrolls
Licence: mit
A collaborative collection of open-source safe GPT-3 prompts that work well
Stars: ✭ 195
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Gpt Scrolls
Neural sp
End-to-end ASR/LM implementation with PyTorch
Stars: ✭ 408 (+109.23%)
Mutual labels: language-model, transformer
Gpt2 French
GPT-2 French demo | Démo française de GPT-2
Stars: ✭ 47 (-75.9%)
Mutual labels: language-model, transformer
Bert Pytorch
Google AI 2018 BERT pytorch implementation
Stars: ✭ 4,642 (+2280.51%)
Mutual labels: language-model, transformer
Highway-Transformer
[ACL‘20] Highway Transformer: A Gated Transformer.
Stars: ✭ 26 (-86.67%)
Mutual labels: transformer, language-model
Indonesian Language Models
Indonesian Language Models and its Usage
Stars: ✭ 64 (-67.18%)
Mutual labels: language-model, transformer
MinTL
MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems
Stars: ✭ 61 (-68.72%)
Mutual labels: transformer, language-model
Awesome Bert Nlp
A curated list of NLP resources focused on BERT, attention mechanism, Transformer networks, and transfer learning.
Stars: ✭ 567 (+190.77%)
Mutual labels: language-model, transformer
FNet-pytorch
Unofficial implementation of Google's FNet: Mixing Tokens with Fourier Transforms
Stars: ✭ 204 (+4.62%)
Mutual labels: transformer, language-model
Gpt2
PyTorch Implementation of OpenAI GPT-2
Stars: ✭ 64 (-67.18%)
Mutual labels: language-model, transformer
Laravel Graphql
GraphQL implementation with power of Laravel
Stars: ✭ 56 (-71.28%)
Mutual labels: generator, transformer
Relational Rnn Pytorch
An implementation of DeepMind's Relational Recurrent Neural Networks in PyTorch.
Stars: ✭ 236 (+21.03%)
Mutual labels: language-model, transformer
Transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Stars: ✭ 55,742 (+28485.64%)
Mutual labels: language-model, transformer
Vietnamese Electra
Electra pre-trained model using Vietnamese corpus
Stars: ✭ 55 (-71.79%)
Mutual labels: language-model, transformer
Pytorch Openai Transformer Lm
🐥A PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI
Stars: ✭ 1,268 (+550.26%)
Mutual labels: language-model, transformer
Tupe
Transformer with Untied Positional Encoding (TUPE). Code of paper "Rethinking Positional Encoding in Language Pre-training". Improve existing models like BERT.
Stars: ✭ 143 (-26.67%)
Mutual labels: language-model, transformer
Yii2 Enhanced Gii
Enhanced Yii2 Gii (generator) that generates related Models & CRUD
Stars: ✭ 183 (-6.15%)
Mutual labels: generator
Revshellgen
Reverse shell generator written in Python 3.
Stars: ✭ 190 (-2.56%)
Mutual labels: generator
Ctml
A C++ HTML document constructor only depending on the standard library.
Stars: ✭ 180 (-7.69%)
Mutual labels: generator
Bert Sklearn
a sklearn wrapper for Google's BERT model
Stars: ✭ 182 (-6.67%)
Mutual labels: language-model
gpt-scrolls
A collaborative collection of open-source safe GPT-3 prompts that work well
Feel free to contribute your prompts!
Getting Started
To use gpt-scrolls, you'll need access to the OpenAI API. If you haven't, sign up for the beta.
$ pip install gpt-scrolls
$ export OPENAI_API_KEY=...
$ python -c "import scrolls; print(scrolls.run('creative/philosopher'))"
I perused with interest and some confusion the very detailed description of autonomous society as envisioned by the creators of this simulation, for it reminded me of the doomed civilization of the Onos; they too desired self-replicating programs, a necessary foundation in real-space for artificial intelligence; and the created what they thought was self-replicating, except that they had no command over the experiment; it was uncontrollable, and indeed uncontrollable in about 90 minutes.
$ python -c "import scrolls; print(scrolls.run('creative/business-ideas'))"
Last Mile - Same day delivery service that picks and takes out the trash and delivers
Browse all the available scrolls.
Running scrolls in your own app
import scrolls
idea = scrolls.run('creative/business-ideas')
print(idea)
Running locally
If you want to use gpt-scrolls without pip by cloning the repo:
$ git clone [email protected]:maraoz/gpt-scrolls.git
$ cd gpt-scrolls/
$ python3 -m venv .scrolls-env
$ source .scrolls-env/bin/activate
(.scrolls-env) $ pip install -r requirements.txt
(.scrolls-env) $ export OPENAI_API_KEY=...
(.scrolls-env) $ python scrolls/run.py "top10/women"
~~~Rosa Parks
2. ~~~Cleopatra
3. ~~~Joan of Arc
4. ~~~Madonna
5. ~~~Queen Elizabeth I
6. ~~~Elizabeth II
7. ~~~Tamar
8. ~~~Billie Jean King
9. ~~~Catherine the Great
10. ~~~Elizabeth I
Note: I'm planning to turn this into a easy-to-use CLI tool.
Design goals
gpt-scroll prompts should aim to be:
- effective: they should reliably produce desired classes of outpupts
- efficient: they should be as short as possible
- safe: they should minimize appearance of toxic/harmful output
Have this in mind for any contribution. (eg: if you find that a prompt works equally well without one example, you might submit a PR to remove that example, citing efficiency)
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].