Simple PDF generation for Python

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.

H-Net: Hierarchical Network with Dynamic Chunking

Superlinked Inference Engine is an Open-source inference server and production cluster for embeddings, reranking, and extraction.

DeepSeek LLM: Let there be answers

A platform for deep learning challenges and AI education. Deep-ML is a website dedicated to making deep learning challenges accessible and engaging. It offers a variety of AI-related problems for l…

Supercharge Your LLM with the Fastest KV Cache Layer

Pytorch implementation of "EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation"

Learn the building blocks of how to build DeepSeek from scratch.

Repair malformed JSON from LLMs, APIs, logs, and user input in Python.

Awesome AI industry & research review

A clean, single-file PyTorch implementation of Attention Residuals (Kimi Team, MoonshotAI, 2026), integrated with Grouped Query Attention (GQA), SwiGLU feed-forward networks, and Rotary Position Em…

Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

AI system design guide for engineers building production AI systems and evals.

Notes of the book System Desgin Interview - An Insider's Guide

Lists of company wise questions. Every csv file in the companies directory corresponds to a list of questions on leetcode for a specific company based on the leetcode company tags. Updated as of 20…

Official Repo for WWW 2025 paper "Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agents"

[ICCV 2023] CLIP-Driven Universal Model; Rank first in MSD Competition.

Warp is an agentic development environment, born out of the terminal.

Synthetic data curation for post-training and structured data extraction

Aligning pretrained language models with instruction data generated by themselves.

ASTRA is an end-to-end system for synthesizing agentic trajectories and rule-verifiable environments for SFT and RL training, developed by Beike Language and Intelligence (BLI).

Go ahead and axolotl questions

An agent that can run everywhere - even in your watch!

[CVPR 2026] This repo contains the code and models of SPECTRE: Self-Supervised & Cross-Modal Pretraining for CT Representation Extraction.

Reference PyTorch implementation and models for DINOv3