# 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/eynhota
yue-fang-readfog
feeds.twtxt.net
View Thread
從頭預訓練一個 LLaMA 3 超級 mini 杯**
作者：Xode 原文：https://zhuanlan.zhihu.com/p/695130168 整理：青稞 AI這次打算用 Hugging Face 的 API 來寫一份預訓練大（小）模型的代碼，也就是用 Trainer 來做預訓練。由於只是想練習一下，因此打算選一個極小模型 + 小數據集。爲了貼近主流，於是打算預訓練一個 LLaMA 3——不過是超迷你版本，大小僅不到 20M ⌘ Read more