Anders's starred repositories
llama3-from-scratch
llama3 implementation one matrix multiplication at a time
StableCascade
Official Code for Stable Cascade
www-project-llm-verification-standard
Project LLM Verification Standard
instant-ngp
Instant neural graphics primitives: lightning fast NeRF and more
PowerInfer
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
mamba-minimal
Simple, minimal implementation of the Mamba SSM in one file of PyTorch.
microagents
Agents Capable of Self-Editing Their Prompts / Python Code
AnimateAnyone
Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation
nakama-godot
Godot client for Nakama server written in GDScript.
build-your-own-x
Master programming by recreating your favorite technologies from scratch.
CyberEngineTweaks
Cyberpunk 2077 tweaks, hacks and scripting framework
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
generative-ai-python
The Gemini API Python SDK enables developers to use Google's state-of-the-art generative AI models to build AI-powered features and applications.