Meta’s Open Source Llama Upsets the AI Horse Race
Huggingface Text Generation Inference adds exllama support
A nice write up for LMQL
Free Open-Source AI LLM Guide
What is better: higher quantiation or higher parameter count?
What determines the format of the prompt template?
Meta’s Llama 2 Elbows Into a Still Very Open Field
(Deleted for not relevant anymore)
llama2.c: Inference Llama 2 in one file of pure C by Andrej Karpathy
Leaked GPT-4 Architecture: Demystifying Its Impact & The 'Mixture of Experts' Explained (with code)
Dolphin (based on Llama 1) released by Eric Hartford!
chargoddard's frankensteined 22B llama2
My attempt at explaining group size and act order simply (but definitely not briefly)
My attempt to explain groupsize and act order in GPTQ
Llama-2, Mo’ Lora (proof of concept MOE of LoRAs)
Llama-2 FOSAI & LLM Roundup Series! (Summer 2023 Edition)
What have you been up to recently with your local LLMs?
Llama 2: Full Breakdown
Llama 2 - Meta AI
