heatdrop.ai

A model-agnostic Python toolkit that handles the boring parts of computer vision: annotations, dataset juggling, and tracking.

A PyTorch implementation of "Attention Is All You Need" that scales from 13M to multi-billion parameter models.

OpenMed packages clinical entity extraction and HIPAA-grade de-identification into models small enough for Apple Silicon and impatient DevOps teams.

Unsloth Studio wraps training, inference, and RL into a single web UI with aggressive memory optimizations.

A step-by-step PyTorch walkthrough that trains a small-but-real LLM on ordinary laptops, no external libraries allowed.

A deliberately minimal GPT-2 implementation that taught a generation how transformers work, now officially succeeded by nanochat.

Karpathy's minimal LLM training harness turns a $43K 2019 training run into a sub-$100 afternoon project.

Ultralytics turned the classic object detector into a unified computer-vision Swiss Army knife you can train via CLI or Python.

A structured prompt library that teaches Claude Code, Codex, or Gemini how to run the full ML research lifecycle — from literature review to LaTeX.

PyTorch is the deep-learning framework that decided Python-first execution beats a static graph.

Companion notebooks for an 800-page quantitative finance textbook, from linear regression to deep reinforcement learning trading agents.

LeRobot standardizes datasets, policies, and hardware control so you can train ACT or VLA models on real arms without rebuilding the plumbing each time.

Hugging Face's Transformers library became the de facto standard for model definitions by being the boring part everyone agrees on.

One framework claims to handle 100+ LLMs and VLMs with zero-code CLI and a web UI—backed by enough quantization methods to make a compression engineer weep.

Google's ML framework wants to be the entire pipeline, not just the model.

A notebook-based workout plan for PyTorch fluency, from linear regression up to building LLM components from scratch.

Reproducible world-model research is usually a pile of glue scripts; this library tries to make it a single import.

Lightricks open-sources the full inference stack and LoRA trainer for their DiT-based audio-video model, complete with camera-control LoRAs and HDR output pipelines.

exo automatically clusters your Apple devices to run frontier models that won't fit on one machine, using Thunderbolt like a datacenter backplane.

MLX-VLM crams speculative decoding, continuous batching, and KV cache quantization into a Mac-native toolkit for running multimodal models locally.