-
Clarity.AI
- London, UK
- https://www.linkedin.com/in/attentioncoach/
Stars
A Windows and Office activator using HWID / Ohook / KMS38 / Online KMS activation methods, with a focus on open-source code and fewer antivirus detections.
Play with OpenAI API's using your own API Key. Your API Key is stored and used only from your browser.
Slack app to spin up / down EC2 instances and optionally mount SageMaker Studio EFS and EBS volumes.
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with LlamaIndex, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
Convert owned Kindle books to PDF without needing a device. Good for viewing on a ReMarkable.
Mamba-Chat: A chat LLM based on the state-space model architecture 🐍
Automatically activate Python virtual environments as you navigate the source code.
Powerful friendly HTTP mock server & proxy library
A module designed for launching an ephemeral, short-lived openvpn instance.
Override create-react-app webpack configs without ejecting
Terraform code to quickly spin up / tear down an EC2 instance in AWS. A persistent EBS volume is also created and mounted at /home.
🔒 Enterprise-grade API gateway that helps you monitor and impose cost or rate limits per API key. Get fine-grained access control and monitoring per user, application, or environment. Supports Open…
Amazon Web Services version 4 authentication for the Python Requests module
OpenAI API proxy for fine-grained cost tracking & control and caching of responses
Reproduce as closely as possible the conditions of running inside an AWS Lambda function container to facilitate testing and debugging.
Use AWS Lambda functions as a proxy pool to scrape web pages with Selenium.
An example starting point monorepo for data sicence teams
Demo to run Google Translate on a PDF file using Selenium and AWS Lambda.
The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.
A JupyterLab extension to jump to the line in the file of the stack trace, search Google for the error in Stack Overflow, or ask Bing Chat for help.
Use Code Llama with Visual Studio Code and the Continue extension. A local LLM alternative to GitHub Copilot.
⚡ Dynamically generated stats for your github readmes
Large Language Model Text Generation Inference
Train Llama 2 & 3 on the SQuAD v2 task as an example of how to specialize a generalized (foundation) model.