The knowledge distillation metagame is getting out of hand! https://developers.googleblog.com/en/smaller-safer-more-transparent-advancing-responsible-ai-with-gemma

Channel
Bag of Words
@dailyBagOfWords
On this record: Growth · Engagement · Reactions · Posts · Polls · Citations · Cite this entry
244subscribers
-2 since we began measuring on 6 August 2026
Risers and fallers across the register · movement among entries of Under 1,000.
Register entry
| Telegram ID | -1001469336260 |
|---|---|
| Type | Channel |
| Username | @dailyBagOfWords |
| Created | Between 1 April 2019 and 30 September 2021 — estimated from Telegram’s id allocation, not measured. How this range is calculated. |
| First recorded | 7 August 2026 |
| Last confirmed live | 11 September 2026 |
| Measurements held | 4 |
| Confirmed unchanged | 3 times, most recently 11 September 2026 |
| On Telegram | t.me/dailyBagOfWords |
Growth
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 27 Aug 2026, 11:53 | 244 | -1 |
| 21 Aug 2026, 01:13 | 245 | -1 |
| 7 Aug 2026, 02:31 | 246 | no change |
| 6 Aug 2026, 17:34 | 246 | first reading |
Engagement
18 posts held, back to 11 June 2023 — 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 18 posts for this entry, the most recent from 1 August 2024. An engagement rate over an empty window would be a number about nothing.
Reaction mix
25 reactions across 8 posts, in 2 distinct kinds. The most used accounts for 76.0% of them.
| Reaction | Count | Share | Share, drawn |
|---|---|---|---|
| 👍 | 19 | 76.0% | |
| 🤣 | 6 | 24.0% |
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 9 of the 18 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 25 reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.
Measured over the 18 most recent posts we hold, published 11 June 2023 to 1 August 2024, using the newest reading held for each. Telegram Stars are excluded: they are a payment, not a reaction, and they have their own section.
Recent posts
Bag of Words pinned «با همین چند خط کد و بدون نیاز به openai یه سیستم RAG روی لپتاپ شخصیتون راه بیاندازین استفاده از RAG به قدری متداول شده که راه انداختن یه llm روی لپتاپ شخصی و سوال و جواب کردن راجع به محتویات فایلها راحتتر از همیشه است! قدم اول اینکه ollama رو نصب و مدل…»
اگر سوالی که پرسیدم رو به صورت کلی از phi3 بپرسم این جواب رو میگیرم: What is the opposite of love? The concept traditionally considered as opposites often relates to emotions and feelings. In this context, the opposite of "love" could be seen as a range of negative human experiences or sentiments that are diametrically opposed in nature; these might include hatred, which is an intense dislike for someone else wit…
با همین چند خط کد و بدون نیاز به openai یه سیستم RAG روی لپتاپ شخصیتون راه بیاندازین استفاده از RAG به قدری متداول شده که راه انداختن یه llm روی لپتاپ شخصی و سوال و جواب کردن راجع به محتویات فایلها راحتتر از همیشه است! قدم اول اینکه ollama رو نصب و مدل مورد علاقتون رو دانلود کنید: ollama run phi3 حالا با همین چند خط میتونین شروع به حرف زدن با فایل یا فایلهای مدنظرتون کنین: from llama_index.core import S…
جستجو نیاز به بازآفرینی دارد؛ آیا رقیب جدیدی برای گوگل وارد بازی شده است؟
برای اولین بار! قدرتمندترین مدل زبانی دنیا، یه مدل متن بازه! - Open Source AI Is the Path Forward - Llama 3.1 - 405B, 70B & 8B with multilinguality and long context - Model Card
گفتگوی جادی با امیر عبدی، دانشمند مدلهای زبانی بزرگ در مایکروسافت https://youtu.be/Gd4qK05CfE8
👍1
مستند کوتاه، جذاب و البته تبلیغاتی برای آشنایی با داستان PyTorch https://www.youtube.com/watch?v=rgP_LBtaUEc
نسخهی بهار از کورس شناخته شدهی CS224N دانشگاه استنفورد، مدتی هست که معرفی شده: https://web.stanford.edu/class/cs224n قبلا هم بارها این کورس رو معرفی کردم، بسیار کورس خوبیه و مرتب با موضوعات و مفاهیم جدیدی که تو صنعت و دانشگاه منتشر میشن، به روز میشه. #NLP
👍5
یکی از ویژگیهای جالب و پرکاربرد #spacy ابزار Span هست. با این ابزار میتونین دستهبندیهای دلخواه به بخشهای مختلفی از متن اختصاص بدید. یکی از کاربردهایی که داره برای مواقعی هست که با ابزارهای مختلف، بخشهای مختلف متنی که در اختیار دارین رو دستهبندی میکنین و همه متادیتای بدست اومده رو داخل خود همون متن ذخیره میکنین! تمیز و شیک.
👍1
حالا که بحث یادگیری #spacy و آشنایی بیشتر باهاش رو قراره پیش ببریم، پیشنهاد میکنم خودتون دست پیش بگیرین و نگاهی به این سری آموزشی خفن و ساده بیاندازین: https://course.spacy.io/en
تو این مدتی که این کانال فعالیتش کمتر شده بود، طبیعتا دنیای NLP دست از کار نکشیده بود. کارپاتی یکی از بهترین آموزشهاش رو منتشر کرد که کمک میکنه به یه درک عمیق و خوب از مفهوم Tokenization برسیم. توصیه میکنم این دو ساعت رو از دست ندین. https://www.youtube.com/watch?v=zduSFxRajkE&t=6433s
👍4
Showing the 12 most recent of 18 posts we hold for @dailyBagOfWords. 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.
Polls
The poll we hold for this entry, as Telegram rendered it when we read the post. A poll’s figures keep moving after that, so each one is dated.
اینجا موافق هستین دوباره فعال شه و بیشتر دربارهی NLP حرف بزنیم؟
- 👍95%
- 👎5%
Shares as published. No per-option vote count is published by Telegram, so none is shown.
Percentages only — there are no per-option vote counts here, because Telegram publishes none. The public post preview gives each option’s share and a single voter total, and nothing else. Multiplying one by the other would produce a per-option tally that looks measured and is not: the shares are rounded to whole numbers before we ever see them. We print what was published and leave the column that does not exist empty.
The shares need not add up to 100. Rounding alone puts many polls at 99 or 101. A poll that allows more than one answer per voter runs well past 100 by design, and several here do. The bars are drawn against a fixed 100% track at each option’s own percentage rather than normalised to the total, so a poll that exceeds it shows that it does instead of being quietly rescaled.
Read from the 18 most recent posts we hold, published 11 June 2023 to 1 August 2024. Telegram labels each poll by kind — an anonymous poll, a quiz, a closed set of final results — and that label is reproduced rather than paraphrased.
Forward network
Republished by
Channels on the register that have forwarded this channel's posts into their own feed.
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.
Cite this entry
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 27 August 2026 — this entry's latest reading, not the date you are reading this.
“Bag of Words” (@dailyBagOfWords), 244 subscribers as measured 27 August 2026. Telegram Register, tgregister.com/channel/dailyBagOfWords.
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.