# I am the Watcher. I am your guide through this vast new twtiverse.
# 
# Usage:
#     https://watcher.sour.is/api/plain/users              View list of users and latest twt date.
#     https://watcher.sour.is/api/plain/twt                View all twts.
#     https://watcher.sour.is/api/plain/mentions?uri=:uri  View all mentions for uri.
#     https://watcher.sour.is/api/plain/conv/:hash         View all twts for a conversation subject.
# 
# Options:
#     uri     Filter to show a specific users twts.
#     offset  Start index for quey.
#     limit   Count of items to return (going back in time).
# 
# twt range = 1 1
# self = https://watcher.sour.is/conv/3wfp3sa
yue-fang-readfog
feeds.twtxt.net
View Thread
現代 LLM 基本技術整理**
0 開始之前本文從 Llama 3 報告出發，基本整理一些現代 LLM 的技術。'基本'，是說對一些具體細節不會過於詳盡，而是希望得到一篇相對全面，包括預訓練，後訓練，推理，又能介紹清楚一些具體技術，例如 RM，DPO，KV Cache，GQA，PagedAttention，Data Parallelism 等等的索引向文章。由於東西比較多，且無法詳盡細節，所以推薦大家二次整理爲自己的筆記。本文的 ⌘ Read more