PulseAugur
中
实时 20:52:46
English(EN) Part 2 of 4, How AI Actually Works: how many r's are in strawberry? To the model it is one token, one number. I ran a real 8B model (Qwen3-8B, 4-bit, llama.cpp)

Qwen3-8B 模型分词过程在 MacBook 上演示

使用 Qwen3-8B 模型演示了大型语言模型如何处理单词,特别是分词过程。实验涉及在 MacBook 上运行模型以记录 token ID 和下一个 token 的概率。通过检查单词如何分解为 token 来探索 AI 的内部工作原理。 AI

影响 阐释了 LLM 中基本的分词过程,这对于理解模型的行为和局限性至关重要。

排序理由 模型分词过程演示。[lever_c_demoted from research: ic=1 ai=1.0]

在 Mastodon — mastodon.social 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

Qwen3-8B 模型分词过程在 MacBook 上演示

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
模型分词过程演示。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
1 days old
Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. Mastodon — mastodon.social TIER_1 English(EN) · R4TSQ ·

    第2部分(共4部分),AI 实际如何运作:草莓中有多少个 r?对模型来说,它是一个 token,一个数字。我运行了一个真实的 8B 模型(Qwen3-8B,4 位,llama.cpp)

    Part 2 of 4, How AI Actually Works: how many r's are in strawberry? To the model it is one token, one number. I ran a real 8B model (Qwen3-8B, 4-bit, llama.cpp) on my MacBook and recorded the real token IDs, the top-20 next-token odds and a temperature dial sampled fifteen times.…