Pythonで学ぶ言語モデルのテキスト生成：TemperatureとTop-k

import math
import random

# Layer normalization rescales a vector to mean 0 and variance 1.
def layer_norm(x, eps=1e-5):
    mean = sum(x) / len(x)
    var = sum((v - mean) ** 2 for v in x) / len(x)
    return [(v - mean) / math.sqrt(var + eps) for v in x]
print("layer norm:", [round(v, 3) for v in layer_norm([2.0, 4.0, 6.0, 8.0])])

# Next-token scores from a model; temperature and top-k shape the choice.
words = ["cat", "dog", "car", "sky"]
logits = [2.0, 1.5, 0.3, -1.0]

def probabilities(temperature=1.0, top_k=None):
    scores = [l / temperature for l in logits]
    if top_k:  # keep only the k best scores
        cutoff = sorted(scores, reverse=True)[top_k - 1]
        scores = [s if s >= cutoff else -1e9 for s in scores]
    exps = [math.exp(s - max(scores)) for s in scores]
    return [e / sum(exps) for e in exps]

for t, k in [(1.0, None), (0.5, None), (1.0, 2)]:
    print(f"temperature={t} top_k={k}:", [round(p, 2) for p in probabilities(t, k)])

random.seed(7)
print("sampled:", random.choices(words, weights=probabilities(0.8, 3), k=5))