Stars
This repository contains blog post for GRPO RL algorithm using simple Grid World environment.
Aegis is a light weight Chrome extension that obfuscates sensitive data like emails, phone numbers, and credit card numbers in real time. It features an intuitive interface for masking and copying …
A high-performance async web crawler that meticulously maps website structures with surgical precision.
Visual Web Pathfinder with Security Analysis Pipeline...Further Penn-test AI agent.
This repository is a first trial of using the Aider agent with GROQ.
This repository contains the code and resources for training the Qwen model using the CODE+MATH dataset
Speculative decoding challenge by anysphere(cursor AI).
This repository demonstrates the end-to-end process of deploying a machine learning model in a JavaScript environment, from training and conversion to integration and prediction.
analysis of company data to identify trends in acquisitions and overall performance across different industries.
This is a Python script designed to help you adjust the timing of subtitles in .srt files. Whether you need to fix sync issues or simply shift the timing, this script will allow you to add or subtr…
I focus on advancing AI for the benefit of humanity. My work includes simplifying complex tasks and developing cutting-edge models in transformers and agents using reinforcement learning.
SpS-SpecDec: a fast Python lib that boosts autoregressive LM inference with speculative decoding. Inspired by DeepMind, it guesses multiple tokens using a small draft model, verifies with a big one…