cramming
askai
cramming | askai | |
---|---|---|
6 | 1,753 | |
1,238 | 86 | |
- | - | |
7.3 | 10.0 | |
16 days ago | over 1 year ago | |
Python | TypeScript | |
MIT License | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
cramming
- [P] Notes on training BERT from scratch on an 8GB consumer GPU
- Cramming the training of a (BERT-type) language model into limited compute
- NanoGPT
-
New AI Research from the University of Maryland Investigates Cramming Challenge for Training a Language Model on a Single GPU in One Day
Quick Read: https://www.marktechpost.com/2023/01/03/new-ai-research-from-the-university-of-maryland-investigates-cramming-challenge-for-training-a-language-model-on-a-single-gpu-in-one-day/ Paper: https://arxiv.org/pdf/2212.14034.pdf Github: https://github.com/JonasGeiping/cramming
- Lucas Beyer on Twitter: “How Good of a Bert Can One Get in One Day on One GPU?
-
Cramming: Training a Language Model on a Single GPU in One Day - Jonas Geiping and Tom Goldstein University of Maryland 2022
Github: https://github.com/JonasGeiping/cramming
askai
- The ChatGPT URL have changed
- Chat.openai.com now redirects (me) to chatgpt.com
-
Unofficial ChatGPT API
This API allows you to interact with ChatGPT programmatically, and I've built some cool agents on top of it. Check out the code and let me know what you think! :
ChatGPT unofficial API :
This project is a Node.js application that interacts with the ChatGPT conversational AI model using Puppeteer, a Node.js library for automating web browsers.
Files chatgptv1.js: This file contains the main logic for the ChatGPT bot, including methods for initializing the browser, sending messages, receiving replies, and handling errors.
bart.js: This file contains a function that uses the Cloudflare API to summarize the conversation history when an error occurs, in order to resume the conversation.
twochatbotsconv.js: This file is simple use of the API , which creates two instances of the ChatGPT class, initiates a conversation between them, and saves the conversation history to a file.
.env: This file contains the API token for the Cloudflare API, which is used in the bart.js file.
Dependencies :
puppeteer: A Node.js library for automating web browsers. fs: The built-in file system module in Node.js. winston: A logging library for Node.js. crypto: The built-in cryptography module in Node.js. axios: A popular HTTP client library for Node.js. dotenv: A zero-dependency module that loads environment variables from a .env file.
Usage:
Install the dependencies by running npm install in your project directory. Create a .env file in the project directory and add your Cloudflare API token:
API_TOKEN=YourfreeCloudFlareAPIToken In your code, create a new instance of the ChatGPT class and use the sendMessage and getReply methods to interact with the ChatGPT model:
const ChatGPT = require('./chatgptv1');
const chatgpt = new ChatGPT(); await chatgpt.initializeBrowser();
await chatgpt.sendMessage('Hello, ChatGPT!'); const reply = await chatgpt.getReply(); console.log(reply);
await chatgpt.closeBrowser(); If an error occurs during the conversation, the handleError method will attempt to save the conversation history and resume the conversation using the summarized context.
Before Running :
run Google chrom in the debug mode using 9220 port , run : google-chrome-stable --remote-debugging-port=9222
Customization :
You can customize the behavior of the ChatGPT bot by passing options to the ChatGPT constructor:
chatbotUrl: The URL of the ChatGPT interface (default: 'https://chat.openai.com/'). headless: Whether to run the browser in headless mode (default: false). saveConversationCallback: A callback function that will be called with the conversation summary and the conversation file name when an error occurs.
License:
This project is licensed under the MIT License.
- It's a shame – chat.openai.com redirect to chatgpt.com is broken
-
Building a Basic Forex Rate Assistant Using Agents for Amazon Bedrock
After wrestling with it for a bit and eventually giving up, I instead turned to ChatGPT to see if it is smart enough for the task. With my free plan, I asked ChatGPT 3.5 the following:
- Learn to ask for help
-
How to build a custom GPT: Step-by-step tutorial
Go to chat.openai.com and log in
- Chat.openai.com no longer requires login
-
Integrating Strapi with ChatGPT and Next.js
In this tutorial, we will learn how to use Strapi, ChatGPT, and Next.js to build an app that displays recipes using AI.
-
GPT-4 Turbo with Vision is a step backwards for coding
Maybe I am bit dim, but how one can choose GPT-4 Turbo? Is this available from https://chat.openai.com/ ?
What are some alternatives?
nanoGPT - The simplest, fastest repository for training/finetuning medium-sized GPTs.
ChatGPT - 🔮 ChatGPT Desktop Application (Mac, Windows and Linux)
english-lang - The English Programming Language
gpt-4chan-model
aitextgen - A robust Python tool for text-based AI training and generation using GPT-2.
openai-cookbook - Examples and guides for using the OpenAI API
flan-ul2-alpaca
ai-cli - Get answers for CLI commands from ChatGPT right from your terminal
askai - Your simple terminal helper - A CLI integration with OpenAI's GPT3
KoboldAI-Client
extreme-bert - ExtremeBERT is a toolkit that accelerates the pretraining of customized language models on customized datasets, described in the paper “ExtremeBERT: A Toolkit for Accelerating Pretraining of Customized BERT”.
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.