Text classification with Foundation Language Model LLaMA
$ git clone https://github.com/sh0416/llama-classification.git▲ +2 ★ this week
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
▲ +6 ★ this week
Build a modern LLM from scratch. Every line commented. Explained like we are five.
▲ +20 ★ this week
Harness LLMs with Multi-Agent Programming
▲ +3 ★ this week
Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization
🩹Editing large language models within 10 seconds⚡
A complete guide to start and improve your LLM skills in 2026 with little background in the field and stay up-to-date with the latest news and state-of-the-art techniques!
Data from GitHub · snapshot Nov 13, 2026