I animated how a language model picks the next token, with real probabilities from Qwen2.5-0.5B: softmax, greedy vs sampling, temperature, top-k, top-p (7 min video) [D]

I made this explainer for my small channel and would like feedback from people learning this, especially if anything is wrong. It follows one real example the whole way. I gave Qwen2.5-0.5B-Instruct "Write one sentence a