Channel
@before_relu_or_after
On this record: Growth · Engagement · What this channel posts · Reactions · Stars · Posts · Citations · Cite this entry
533subscribers
+0 since we began measuring on 7 August 2026
Risers and fallers across the register · movement among entries of Under 1,000.
| Telegram ID | -1001734083330 |
|---|---|
| Type | Channel |
| Username | @before_relu_or_after |
| Description | В основном про ускорение нейронок, но иногда и про смежные темы. |
| Created | Between 1 December 2021 and 30 April 2023 — estimated from Telegram’s id allocation, not measured. How this range is calculated. |
| First recorded | 7 August 2026 |
| Last confirmed live | 15 September 2026 |
| Measurements held | 2 |
| On Telegram | t.me/before_relu_or_after |
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 7 Aug 2026, 11:03 | 533 | no change |
| 7 Aug 2026, 08:48 | 533 | first reading |
20 posts held, back to 9 January 2024 — the reader has not yet reached the start of this channel’s public history, so older posts may sit further back, unread. Read across 1 page of Telegram’s post history, 20 posts per page.
Nothing published in the last 30 days. ERR and ER are rolling 30-day measures, so there is nothing to compute — we hold 20 posts for this entry, the most recent from 11 July 2026. An engagement rate over an empty window would be a number about nothing.
Lifetime counters from Telegram’s own channel header, read 7 August 2026 — not the date at the top of this page, which is when the subscriber count was last read. Below Telegram’s rounding threshold, so these counts are exact.
576 reactions across 20 posts, in 1 kind.
| Reaction | Count | Share | Share, drawn |
|---|---|---|---|
| 🤡 | 576 | 100.0% |
No sentiment is inferred, and none should be read in. This table is ordered by count and by nothing else. Emoji do not carry stable meaning across languages or communities — 🙏 is thanks in one channel and mourning in another — so we publish which ones were pressed and how often, and pass no judgement on what an audience meant by them.
Precision. Telegram publishes reaction counts per emoji and short-forms each one — 4.34K, 1.2M — so any single kind at or above 1,000 reaches us at three significant figures, and only counts below 1,000 are exact. The shares above are ratios of those figures and carry the same error. This is also why the total here can differ slightly from a reaction total printed elsewhere on the page: both are sums of the same rounded parts, taken over samples with different edges.
Coverage. Reactions were read on 20 of the 20 sampled posts in this sample. Summed by Telegram’s own count on each post — not by adding up the per-emoji breakdown above — those same posts carry 576 reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.
Measured over the 20 most recent posts we hold, published 9 January 2024 to 11 July 2026, using the newest reading held for each. Telegram Stars are excluded: they are a payment, not a reaction, and they have their own section.
A paid reaction is a reader spending Telegram Stars — bought with money — on a post by @before_relu_or_after. Telegram publishes the count on the public post preview alongside ordinary reactions, and this register reads it there. It is the only figure on this site that measures money moving rather than attention.
Stars are not reactions, and the two are never added. They are rendered in the same strip on Telegram and counted in the same shape, but one is a tap and the other is a purchase. The reaction totals and the engagement rate elsewhere on this page exclude every figure in this section, and no rate here is computed against a reaction count.
This is not revenue, and we publish no currency figure. What a Star costs a reader and what it pays a channel are different numbers, Telegram takes a share we cannot observe, and the terms have changed. Converting a Star count into money would be an estimate dressed as a measurement, so the count is where we stop.
Counted over the 20 most recent posts we hold for this entry, published 9 January 2024 to 11 July 2026. Star counts above 1,000 reach us in Telegram’s short form and carry the same three-significant-figure rounding as everything else on this page.
Здравствуйте, дорогие подписчики! Сделали пособие для своих студентов (как всегда своевременно), как изобрести трансформеры (и в частности, механизм внимания), ничего не зная про NLP. Строгого вывода, понятное дело, нет и не может быть, но надеемся, что это даст некую "инженерную интуицию" про эту архитектуру. https://buildin.ai/share/fa11d0dd-6ad1-4cf5-ac0f-0a11c7504d99?code=JFGWXK [Buildin.AI]Attention! No NLP he…
🤡26
Дорогие подписчики! Администрация канала от всей души поздравляет вас с Новым Годом! 🎅 В новом году желаем вам карьерного роста, физического и ментального здоровья, а также всего хорошего! ⛄️ Stay hydrated and sleep well! HNY!!! 🌲
🤡33
Чувак у меня на курсе обнаружил приколдесное свойство. Допустим, у вас есть величина y, которая y = softmax(z) Как получить x = softmax(z / T)? Оказывается, это просто x = softmax(y.log() / T). Пусть: z = [z_1, z_2] softmax(z) = [exp(z_1) / (exp(z_1)+exp(z_2)), exp(z_2) / (exp(z_1)+exp(z_2))] Но exp(z_1)+exp(z_2) - это нормировочная константа, С. Тогда: softmax(z) = [exp(z_1) / C, exp((z_2) / C] softmax(z).log()…
🤡49
Здравствуйте, дорогие подписчики! Сегодня поговорим с вами про быстрые трекеры https://buildin.ai/share/d74efe64-f67c-4dbb-953a-00151a96f237?code=JFGWXK [BuildIn.AI]FEAR: Fast, Efficient, Accurate and Robust Visual Tracker
🤡24
Posted without readable text
🤡38
Дорогие подписчики! Администрация канала от всей души поздравляет вас с Новым Годом! 🎅 В новом году желаем вам карьерного роста, физического и ментального здоровья, а также всего хорошего! ⛄️ Stay hydrated and sleep well! HNY!!! 🌲
🤡53
Здравствуйте, дорогие подписчики! В последний день лета предлагаем вам почитать про современное состояние дел в области бинарных трансформеров: https://before-relu-or-after.notion.site/522f887ad1ea4dc08ad33573269fea3b
🤡25
Здравствуйте, дорогие подписчики! Сделали для вас обзор 2 методов квантования. Особенно рекомендуем обратить внимание на QuIP, так как в будущем сделаем обзор на его наследника, QuIP#. Да и вообще, метод incoherence processing станет стандартом при квантовании по нашему мнению, типа как руки после улицы вымыть. https://deepschool-pro.notion.site/LLM-Part-1-e30fecd9f73a4bfa8c09020cc1726e1d?pvs=74
🤡21
Здравствуйте, дорогие подписчики! Делимся с вами прошедшим вебинаром по "Эффективным механизмам внимания". Рекомендуем почитать дискуссию, которая возникла в комментариях к трансляции, там можно найти парочку интересных моментов к размышлению. Слайды, видео.
🤡22
Здравствуйте, дорогие подписчики! Рекомендуем посетить данное 👇 он-лайн мероприятие!
🤡23
Лекция по быстрым механизмам внимания в это воскресенье Главное препятствие на пути к быстрым трансформерам — квадратичный attention. В базовом варианте трансформеры довольно прожорливые как по времени, так и по памяти. Поэтому инженеры ищут способы ускорить attention. О некоторых из них мы расскажем на лекции в воскресенье. Обсудим быстрые механизмы внимания с точки зрения простых инженерных решений. Без математик…
🤡28
В эту субботу я выступаю на DataFest с докладом “Как не разориться и сделать хороший синтез речи”. Выступление будет онлайн, в 12:00. Расскажу почему вообще в синтез речи кто-то готов вкладывать крупные деньги. Где там сходится экономика и как её оптимизирую обычно я и где её сможете применить вы. Нанимать джунов или сеньоров, использовать SOTA или древнючий такотрон 2, покупать свои видюхи или арендовать - всё это …
🤡19
Showing the 12 most recent of 20 posts we hold for @before_relu_or_after. View and reaction counts are the latest single reading for each post, not a live figure, and a recent post is still accumulating both. A view count marked ≈ was rounded by Telegram before we ever saw it — t.me prints views in full below 1,000 and to three significant figures above, so ≈1,200,000 means somewhere between 1,150,000 and 1,249,999. Unmarked counts are exact. Text is reproduced from the public post preview and truncated for length.
Stars beside a post are paid reactions — Telegram Stars, bought with money and spent on that post. They are a different unit from reactions and are never added to them, here or anywhere else on this page.
Republished by
Channels on the register that have forwarded this channel's posts into their own feed.
Republishes
Channels on the register whose posts this channel has forwarded.
Built only from forwarded posts we have actually read, on both sides. Coverage is early and deliberately incomplete: a missing link means we have not read the post that would prove it, never that the relationship does not exist. Counts are distinct forwarded posts observed, so they only ever go up as we read more.
A live page changes as we take new readings, so a citation should name the measurement it is based on, not just the URL. The line below cites the subscriber count as measured 7 August 2026 — this entry's latest reading, not the date you are reading this.
“До ReLU или после?” (@before_relu_or_after), 533 subscribers as measured 7 August 2026. Telegram Register, tgregister.com/channel/before_relu_or_after.
Full measurement history, CC BY 4.0. Every reading this register holds for this entry, not just the latest one, as a dated, downloadable record: CSV · JSON. Free to use with attribution to tgregister.com. Each file carries its own generation timestamp, which is the figure to cite for exactly when the data was retrieved.