Show HN: MinLlama – Llama 3.2 inference in ~100 lines of NumPy (opens in new tab)
Yet Another Llama 3.2 implementation (in pure numpy) - timothygao8710/minLlama
Read the original articleYet Another Llama 3.2 implementation (in pure numpy) - timothygao8710/minLlama
Read the original article