https://x.com/i/status/2086838894494896425
Signed MohammadMojtaba Roshani

Channel
@mmroshani_kb
On this record: Growth · Engagement · What this channel posts · Reactions · Posts · Citations · Cite this entry
15subscribers
+0 since we began measuring on 7 August 2026
Risers and fallers across the register · movement among entries of Under 1,000.
| Telegram ID | -1002194512407 |
|---|---|
| Type | Channel |
| Username | @mmroshani_kb |
| Description | - Mohammad Mojtaba Roshani (mmRoshani) - Distributed System & Learning Engineer / Researcer - mmRoshani.ir (mmroshani.github.io) - linkedin.com/in/mmRoshani - x.com/mmRoshani |
| Created | Between 1 June 2024 and 30 September 2024— estimated from Telegram’s id allocation, not measured. How this range is calculated. |
| First recorded | 11 August 2026 |
| Last confirmed live | 16 August 2026 |
| Measurements held | 2 |
| On Telegram | t.me/mmroshani_kb |
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 11 Aug 2026, 23:30 | 15 | no change |
| 7 Aug 2026, 22:10 | 15 | first reading |
17 posts held, back to 1 April 2026 — 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 pageof Telegram’s post history, 20 posts per page.
ERR is average views per post over the last 30 days divided by subscribers, the definition TGStat uses, so this figure is comparable with the one you will see elsewhere. It falls structurally as a channel grows: a high ERR on a small channel and a low one on a large channel describe reach mathematics, not quality. We publish the figure and the sample it came from and pass no verdict on it.
ER is defined industry-wide as (forwards + reactions + comments) ÷ views— note the denominator is views, not subscribers. Telegram’s public web preview carries views and reactions but not forward or comment counts, so the reaction rate above is the reactions term only and is therefore a floor: the true ER for this channel is higher by an amount we have not measured and will not estimate. It is computed over the 1 of 4 measured posts that carry a reaction reading, and over those same posts' views.
| Window | Rolling 30 days · latest post in window 11 August 2026 |
|---|---|
| Posts held | 17 (1 April 2026 – 11 August 2026) |
| Views total | 74 |
| Reactions total | 1 |
| Forwards / comments | not exposed by the public surface — not measured, not estimated |
| Readings taken | 11 Aug 2026, 23:30 UTC |
Views are a single reading per post, taken at the time above. A post published in the last day or two is still accumulating views, which pulls the 30-day average down slightly. That is a property of the standard definition rather than a fault in it, so we keep the definition rather than “correcting” the number into something nobody can reproduce.
Precision. Telegram publishes view counts on its public widget in short form — 8.12K, 3.7M — so any reading at or above 1,000 reaches us rounded to three significant figures, and only counts below 1,000 are exact. Averages and rates derived from them are shown to the same precision rather than to the unit: a figure like 3,701,250 would assert digits nobody measured.
Reaction counts are published per emoji and rounded the same way, so a total below 1,000 is exact and a larger one is a sum that may carry a rounded component from each emoji above 1,000. Because it is a sum, it does not look rounded — read a large reaction total as three significant figures per contributing emoji rather than as the figure it prints.
Lifetime counters from Telegram’s own channel header, read 11 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.
Measured directly from 3 videos with a duration reading, out of the posts we hold for this channel — not this channel’s whole posting history, only the sample this register has actually read. An exact reading to the second, taken from the post itself rather than from Telegram’s own rounded chrome, so it carries no ≈ mark.
3 reactions across 3 posts, in 2 distinct kinds. The most used accounts for 66.7% of them.
| Reaction | Count | Share | Share, drawn |
|---|---|---|---|
| 👍 | 2 | 66.7% | |
| 🔥 | 1 | 33.3% |
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 3 of the 17 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 3reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.
Measured over the 17 most recent posts we hold, published 1 April 2026 to 11 August 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.
https://x.com/i/status/2086838894494896425
Signed MohammadMojtaba Roshani
𝗦𝗶𝗺𝗽𝗹𝗲 𝗟𝗟𝗠 𝗺𝗲𝘁𝗿𝗶𝗰𝘀 𝗮𝗿𝗲 𝗻𝗼𝘁 𝗲𝗻𝗼𝘂𝗴𝗵... I recently 𝗽𝘂𝗯𝗹𝗶𝘀𝗵𝗲𝗱 a 𝘁𝗲𝗰𝗵𝗻𝗶𝗰𝗮𝗹 𝗱𝗲𝗲𝗽-𝗱𝗶𝘃𝗲 on 22 critical 𝘃𝗟𝗟𝗠 metrics. Visit the live metric dashboard: https://mmroshani.ir/sandbox/vllm-metrics-dashboard.html To truly 𝗼𝗽𝘁𝗶𝗺𝗶𝘇𝗲 for 𝘀𝗰𝗮𝗹𝗲, engineering teams require 𝗴𝗿𝗮𝗻𝘂𝗹𝗮𝗿 𝘃𝗶𝘀𝗶𝗯𝗶𝗹𝗶𝘁𝘆 into how their infrastructure 𝗵𝗮𝗻𝗱𝗹𝗲𝘀 𝗹𝗮𝘁𝗲𝗻𝗰𝘆, 𝘁𝗵𝗿𝗼𝘂𝗴𝗵𝗽𝘂𝘁, and 𝗚𝗣𝗨 𝗺𝗲𝗺𝗼𝗿𝘆 saturation. If you are 𝗯𝘂𝗶𝗹𝗱𝗶𝗻𝗴 or 𝘀𝗰𝗮𝗹𝗶𝗻𝗴 𝗔𝗜 𝗶𝗻𝗳𝗿𝗮𝘀𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲, this 𝗯𝗹𝗼…
Signed MohammadMojtaba Roshani
Turing Complete Transformers Universal Transformers (A.K.A. Weight-Shared Transformers) Instead of having 12 layers with different weights, a Universal #Transformer has one layer that it loops the data through repeatedly (recurrently). By sharing weights across steps, the network learns an algorithm rather than a fixed set of pattern filters. Research has mathematically proven that Universal Transformers are Turi…
Signed MohammadMojtaba Roshani
بنده جزو طرفداران نسیم طالب نیستم، امروز اما این کوت ازش رو در توییتر دیدم و خوشم اومد. فحوای فارسی کلامش میشه این که: نسبت آکادمی به دانش، مثل نسبت تنفروشی به عشق است؛ در ظاهر شاید مو نزنند، اما آدم اگر مال این صحبتها باشد و کلاه سرش نرود، میفهمد که اصلا و ابدا یک چیز نیستند منظورش اینه که عشق یک حس درونی و خالص و عمیقه. در حالی که تنفروشی شکل تجاری و سطحی و معاملهگرایانه اونه. عشق به فهمیدن یک امری جوشیده از…
👍1
Signed MohammadMojtaba Roshani
https://youtube.com/shorts/raUm7RAS7Qs?si=d7YT7jFpJKpouBt5
Signed MohammadMojtaba Roshani
It was a privilege to serve as one of the Top Reviewers for the Trustworthy AI for Good (AI4GOOD) Workshop at ICML 2026, taking place July 10 in Seoul. Reviewing for this workshop was genuinely rewarding. The submissions pushed me to think harder about a question I care about deeply: not just what our AI systems can do in isolation, but what they actually do once they’re out in the world, shaping institutions, infor…
Signed MohammadMojtaba Roshani
http://youtube.com/post/UgkxVawIKSGPg5-CiRO0mX6icWDZ73vBvGy1?surface=shorts&data=AXmpSAEwZ3GnTZhb6GjrTp6oDEX9OZdDfR3KC7gfKG_Lwck4LDVlLzrcrdizkQuimGXnAD-BtixcO0Xf&si=t0X6TnmVU3ZDnqMy
Signed MohammadMojtaba Roshani
http://youtube.com/post/UgkxqTGaLG5hGN2jkXOrMBs9GAO4DLVAE_iy?surface=shorts&data=AXmpSAHz42nzUjqo1O63iY2xNB5jT0xmLqV3SefTDHk4RfRqhJ3xe25DfL7LQ0ygbxQMpT_lZh9wFN3L&si=U9mWqIa9oIT30aCy
Signed MohammadMojtaba Roshani
https://www.linkedin.com/posts/fozouni_mlsecops-ai-cybersecurity-ugcPost-7467903702045974528-pUnU/?utm_source=social_share_send&utm_medium=android_app&rcm=ACoAAC6vwsMBokF8wQs8grFoWcXRl9cQ4FMjmcY&utm_campaign=share_via
Signed MohammadMojtaba Roshani
https://www.linkedin.com/posts/check-out-the-the-detailed-technical-report-share-7468095944392085504-96F_/?utm_source=social_share_send&utm_medium=android_app&rcm=ACoAAC6vwsMBokF8wQs8grFoWcXRl9cQ4FMjmcY&utm_campaign=share_via
Signed MohammadMojtaba Roshani
Testing LLM Outputs: A Hands-On Guide to DeepEval Metrics https://www.linkedin.com/pulse/testing-llm-outputs-hands-on-guide-deepeval-metrics-serhii-smetanskyi-jjtof?utm_source=share&utm_medium=member_android&utm_campaign=share_via
👍1
Signed MohammadMojtaba Roshani
قبل از اینکه مدلهای سنگین رو دانلود کنید، اول مطمئن بشید که واقعاً اجرا میشن ابزار llmfit یه ابزار خط فرمانه (CLI) که خودش سختافزار شما رو تشخیص میده و 206 تا مدل رو بر اساس اینکه واقعاً روی سیستمتون اجرا میشن یا نه، رتبهبندی میکنه. اول CPU، RAM، GPU و VRAM رو بررسی میکنه، بعد همه مدلها رو با سختافزار شما میسنجه و امتیاز میده. میتونین بهصورت TUI تعاملی باهاش مدلها رو ببینین، یا تو حالت CLI یه جدو…
Signed MohammadMojtaba Roshani
Showing the 12 most recent of 17 posts we hold for @mmroshani_kb. 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.
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.
Names
Channels on the register whose handles appear in this channel's posts.
A mention is a weaker signal than a forward and is counted separately for that reason — naming a channel is not republishing it, and a handle in a post body is easy to place deliberately. The post counts beside each row below are distinct posts in which the handle appeared, from posts we have read on both sides — the “Named by N registered channels” figure above is a different count, of distinct NAMING CHANNELS rather than posts, and is not the sum of the rows under it.
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 11 August 2026 — this entry's latest reading, not the date you are reading this.
“mmRoshani” (@mmroshani_kb), 15 subscribers as measured 11 August 2026. Telegram Register, tgregister.com/channel/mmroshani_kb.
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.