mrudeOC
Follow
Stars
Fork of https://github.com/getAsterisk/deepclaude, with added features.
Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory! 🦥
verl: Volcano Engine Reinforcement Learning for LLMs
An inverse rendering framework for tomographic volumetric additive manufacturing
Recipes to scale inference-time compute of open models
Python APIs for web automation, testing, and bypassing bot-detection.
Learning in infinite dimension with neural operators.
Ongoing Lean formalisation of the proof of Fermat's Last Theorem
Fullstack app framework for web, desktop, mobile, and more.
Symile is a flexible, architecture-agnostic contrastive loss that enables training modality-specific representations for any number of modalities.
Benchmark gene representations from different model families
This repository goes over how to handle massive variety in data engineering
Adds nostalgic Pokémon sprites to your VS Code/Cursor window
The official Python SDK for Model Context Protocol servers and clients
The official Typescript SDK for Model Context Protocol servers and clients
Model Context Protocol Servers
Active Learning for Text Classification in Python
pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidb.ai
This repository provides the code and model checkpoints for AIMv1 and AIMv2 research projects.
A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.
Leveraging BERT and c-TF-IDF to create easily interpretable topics.
code for arxiv paper: Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answering
A tool for generating .pex (Python EXecutable) files, lock files and venvs.
Proxmox VE Helper-Scripts (Community Edition)
LLM-powered multiagent persona simulation for imagination enhancement and business insights.
Simple Google Meet transcripts. Private and open source.