Uploaded March 2025 | Updated November 2026, 3 hours ago
Sign up for NVIDIA GTC2025 here!
nvda.ws/48s4tmc
Join The RTX4080 SUPER Giveaway (enter between March 17-21st)
https://forms.gle/TbGgoD5obn1zRz5r7
All you have to do is to take a selfie of you participating in any of their live sessions, and submit it to my form to be eligible to win the prize!
My Newletter
mail.bycloud.ai
My Patreon
patreon.com/c/bycloud
DeepSeek open source week is probably the biggest open source collection we have ever seen, especially in recent years. Their focus on optimization has gave insane performance boost to their LLM inference, yet it is a bit difficult for everyone to understand their open source projects’ impacts. So in this video, I’ll be going through what each of the repository they open sourced does, and how it would impact the AI industry.
DeepSeek Open Source Week GitHub Overview
github.com/deepseek-ai/open-infra-index
This video is supported by the kind Patrons & YouTube Members:
🙏Andrew Lescelius, Ben Shaener, Chris LeDoux, Miguilim, Deagan, FiFaŁ, Robert Zawiasa, Marcelo Ferreira, Owen Ingraham, Daddy Wen, Tony Jimenez, Panther Modern, Jake Disco, Demilson Quintao, Penumbraa, Shuhong Chen, Hongbo Men, happi nyuu nyaa, Carol Lo, Mose Sakashita, Miguel, Bandera, Gennaro Schiano, gunwoo, Ravid Freedman, Mert Seftali, Mrityunjay, Richárd Nagyfi, Timo Steiner, Henrik G Sundt, projectAnthony, Brigham Hall, Kyle Hudson, Kalila, Jef Come, Jvari Williams, Tien Tien, BIll Mangrum, owned, Janne Kytölä, SO, Richárd Nagyfi, Hector, Drexon, Claxvii 177th, Inferencer, Michael Brenner, Akkusativ, Oleg Wock, FantomBloth, Thipok Tham, Clayton Ford, Theo, Handenon, Diego Silva, mayssam, Kadhai Pesalam, Tim Schulz, jiye, Anushka, Henrik Sundt, Julian Aßmann, Thomas Lin, Sid_Cypher, Mark Buckler, Kevin Tai, NO U, Gonzalo Fidalgo, Igor Alvarez, Alon Pluda, Clément Veyssière, Sander Zwaenepoel, etrotta, Binnie Yiu, Matej Macak, c zhou, Berhane-Meskel, sai sandeep mandava, Leo, Asad Dhamani, Charlie C, tantan assawade, Ângelo Fonseca, Stefan Lorenz, Paperboy, mika, Leo, Utsav Soi
[Discord] discord.gg/NhJZGtH
[Twitter] twitter.com/bycloudai
[Patreon] patreon.com/bycloud
[Business Inquiries] bycloudai@gmail.com
[Profile & Banner Art] twitter.com/pygm7
[Video Editor] @Booga04 and me
[Bitcoin (BTC)] 3JFMJQVGXNA2HJE5V9qCwLiqy6wHY9Vhdx
[Ethereum (ETH)] 0x3d784F55E0bE5f35c1566B2E014598C0f354f190
[Litecoin (LTC)] MGHnqALjyU2W6NuJSSW9fTWV4dcHfwHZd7
[Bitcoin Cash (BCH)] 1LkyGfzHxnSfqMF8tN7ZGDwUTyBB6vcii9
[Solana (SOL)] 6XyMCEdVhtxJQRjMKgUJaySL8cGoBPzzA2NPDMPfVkKN
[Ko-fi] ko-fi.com/bycloudai
Sign up for NVIDIA GTC2025 here!
nvda.ws/48s4tmc
Join The RTX4080 SUPER Giveaway (enter between March 17-21st)
https://forms.gle/TbGgoD5obn1zRz5r7
All you have to do is to take a selfie of you participating in any of their live sessions, and submit it to my form to be eligible to win the prize!
My Newletter
mail.bycloud.ai
My Patreon
patreon.com/c/bycloud
DeepSeek open source week is probably the biggest open source collection we have ever seen, especially in recent years. Their focus on optimization has gave insane performance boost to their LLM inference, yet it is a bit difficult for everyone to understand their open source projects’ impacts. So in this video, I’ll be going through what each of the repository they open sourced does, and how it would impact the AI industry.
DeepSeek Open Source Week GitHub Overview
github.com/deepseek-ai/open-infra-index
This video is supported by the kind Patrons & YouTube Members:
🙏Andrew Lescelius, Ben Shaener, Chris LeDoux, Miguilim, Deagan, FiFaŁ, Robert Zawiasa, Marcelo Ferreira, Owen Ingraham, Daddy Wen, Tony Jimenez, Panther Modern, Jake Disco, Demilson Quintao, Penumbraa, Shuhong Chen, Hongbo Men, happi nyuu nyaa, Carol Lo, Mose Sakashita, Miguel, Bandera, Gennaro Schiano, gunwoo, Ravid Freedman, Mert Seftali, Mrityunjay, Richárd Nagyfi, Timo Steiner, Henrik G Sundt, projectAnthony, Brigham Hall, Kyle Hudson, Kalila, Jef Come, Jvari Williams, Tien Tien, BIll Mangrum, owned, Janne Kytölä, SO, Richárd Nagyfi, Hector, Drexon, Claxvii 177th, Inferencer, Michael Brenner, Akkusativ, Oleg Wock, FantomBloth, Thipok Tham, Clayton Ford, Theo, Handenon, Diego Silva, mayssam, Kadhai Pesalam, Tim Schulz, jiye, Anushka, Henrik Sundt, Julian Aßmann, Thomas Lin, Sid_Cypher, Mark Buckler, Kevin Tai, NO U, Gonzalo Fidalgo, Igor Alvarez, Alon Pluda, Clément Veyssière, Sander Zwaenepoel, etrotta, Binnie Yiu, Matej Macak, c zhou, Berhane-Meskel, sai sandeep mandava, Leo, Asad Dhamani, Charlie C, tantan assawade, Ângelo Fonseca, Stefan Lorenz, Paperboy, mika, Leo, Utsav Soi
[Discord] discord.gg/NhJZGtH
[Twitter] twitter.com/bycloudai
[Patreon] patreon.com/bycloud
[Business Inquiries] bycloudai@gmail.com
[Profile & Banner Art] twitter.com/pygm7
[Video Editor] @Booga04 and me
[Bitcoin (BTC)] 3JFMJQVGXNA2HJE5V9qCwLiqy6wHY9Vhdx
[Ethereum (ETH)] 0x3d784F55E0bE5f35c1566B2E014598C0f354f190
[Litecoin (LTC)] MGHnqALjyU2W6NuJSSW9fTWV4dcHfwHZd7
[Bitcoin Cash (BCH)] 1LkyGfzHxnSfqMF8tN7ZGDwUTyBB6vcii9
[Solana (SOL)] 6XyMCEdVhtxJQRjMKgUJaySL8cGoBPzzA2NPDMPfVkKN
[Ko-fi] ko-fi.com/bycloudai
![Why would anyone let LLMs predict 4 tokens at once? Multi-Token Prediction Explained
Check out LTX Video 13B now and experience the latest video gen breakthrough: https://bit.ly/ltxvbycloud
My Newsletter
https://mail.bycloud.ai/
my project: find, discover & explain AI research semantically
https://findmypapers.ai/
My Patreon
https://www.patreon.com/c/bycloud
Future Lens
[Paper] https://arxiv.org/abs/2311.04897
Multi-Token Prediction
[Paper] https://arxiv.org/abs/2404.19737
DeepSeek-V3
[First Paper] https://arxiv.org/abs/2412.19437
[Technical Paper] https://arxiv.org/abs/2505.09343
Try out my new fav place to learn how to code https://scrimba.com/?via=bycloudAI
This video is supported by the kind Patrons & YouTube Members:
🙏Nous Research, Chris LeDoux, Ben Shaener, DX Research Group, Poof N Inu, Andrew Lescelius, Deagan, Robert Zawiasa, Ryszard Warzocha, Tobe2d, Louis Muk, Akkusativ, Kevin Tai, Mark Buckler, NO U, Tony Jimenez, Ângelo Fonseca, jiye, Anushka, Asad Dhamani, Binnie Yiu, Calvin Yan, Clayton Ford, Diego Silva, Etrotta, Gonzalo Fidalgo, Handenon, Hector, Jake Disco very, Michael Brenner, Nilly K, OlegWock, Daddy Wen, Shuhong Chen, Sid_Cipher, Stefan Lorenz, Sup, tantan assawade, Thipok Tham, Thomas Di Martino, Thomas Lin, Richárd Nagyfi, Paperboy, mika, Leo, Berhane-Meskel, Kadhai Pesalam, mayssam, Bill Mangrum, nyaa
[Discord] https://discord.gg/NhJZGtH
[Twitter] https://twitter.com/bycloudai
[Patreon] https://www.patreon.com/bycloud
[Business Inquiries] bycloud@smoothmedia.co
[Profile & Banner Art] https://twitter.com/pygm7
[Video Editor] @Booga04
[Ko-fi] https://ko-fi.com/bycloudai Why would anyone let LLMs predict 4 tokens at once? Multi-Token Prediction Explained](https://i.ytimg.com/vi/4BhZZYg2_J4/mqdefault.jpg)
![This Simple Trick Made ALL LLMs 2x Faster
Try out and get your free credits now on GenSpark AI, as well as unlimited use of AI Chat and AI Image in 2026 for paid users using this link: https://www.genspark.ai/?utm_source=yt&utm_campaign=bycloudAI
In this video, let us demystify one of the coolest trick that researchers use to speedup LLMs so that we can now use it at 2-3x the speed with no drawbacks at all!
my latest project: Intuitive AI Academy
We just wrote a new piece on Distillation & MoE!
https://intuitiveai.academy/
limited time code EARLY for 40% off yearly plan!
My Newsletter
https://mail.bycloud.ai/
My Patreon
https://www.patreon.com/c/bycloud
Speculative Decoding
[Paper 1] https://arxiv.org/pdf/2211.17192
[Paper 2] https://arxiv.org/pdf/2302.01318
Speculative Speculative Decoding
[Paper] https://arxiv.org/abs/2603.03251
Try out my new fav place to learn how to code https://scrimba.com/?via=bycloudAI
This video is supported by the kind Patrons & YouTube Members:
🙏Spam Maj, Alex, Chris LeDoux, DX Research Group, Poof N Inu, Deagan, Robert Zawiasa, Ryszard Warzocha, Tobe2d, Louis Muk, Akkusativ, Kevin Tai, Mark Buckler, NO U, Tony Jimenez, Ângelo Fonseca, jiye, Anushka, Asad Dhamani, Binnie Yiu, Calvin Yan, Clayton Ford, Diego Silva, Etrotta, Gonzalo Fidalgo, Handenon, Hector, Jake Disco very, Michael Brenner, Nilly K, OlegWock, Daddy Wen, Shuhong Chen, Sid_Cipher, Stefan Lorenz, Sup, tantan assawade, Thipok Tham, Thomas Di Martino, Thomas Lin, Richárd Nagyfi, Paperboy, mika, Leo, Berhane-Meskel, Kadhai Pesalam, mayssam, Bill Mangrum, nyaa, Toru Mon, Lame Plane, Matej Macak, Len Mo, saylikhapekar, ZyanSheep
[Discord] https://discord.gg/NhJZGtH
[Twitter] https://twitter.com/bycloudai
[Patreon] https://www.patreon.com/bycloud
[Business Inquiries] bycloud@smoothmedia.co
[Profile & Banner Art] https://twitter.com/pygm7
[Video Editor]
[Ko-fi] https://ko-fi.com/bycloudai This Simple Trick Made ALL LLMs 2x Faster](https://i.ytimg.com/vi/4Ij9YOyrNdM/mqdefault.jpg)
![How RAG Turns AI Chatbots Into Something Practical
Check out ThinkBuddy using the code BYCLOUD in the link: https://thinkbuddy.ai/ltd to get your discount!
my newsletter: https://mail.bycloud.ai/
Retrieval augmented generation, a current popular method to utilize LLMs to retrieve from a database instead of putting everything in a context window. But how does it work? Today I will walk through the most basic idea of RAG and the current meta of how RAG is used, and what it is composed of.
My own RAG experiment on 1TB of PDFs:
https://youtu.be/KL5Au8pKJ38
some papers
[Web + RAG] https://arxiv.org/abs/2408.07611
[Vector + KG RAG] https://arxiv.org/abs/2408.04948
[RAG Survey] https://arxiv.org/abs/2404.10981
[Knowledge Graph for RAG] https://docs.llamaindex.ai/en/stable/examples/query_engine/knowledge_graph_rag_query_engine/
[LlamaIndex] https://www.llamaindex.ai/
[LlamaParse] https://docs.llamaindex.ai/en/stable/llama_cloud/llama_parse/
[HuggingFace] https://huggingface.co/models
[Cohere Command R+] https://docs.cohere.com/docs/command-r-plus
[Cohere Rerank] https://docs.cohere.com/docs/overview
[Cohere Embedding Models] https://cohere.com/blog/introducing-embed-v3
[GraphRAG] https://github.com/microsoft/graphrag
[RAGAS] https://github.com/explodinggradients/ragas
This video is supported by the kind Patrons & YouTube Members:
🙏Andrew Lescelius, alex j, Chris LeDoux, Alex Maurice, Miguilim, Deagan, FiFaŁ, Robert Zawiasa, Owen Ingraham, Tanaro, Daddy Wen, Tony Jimenez, Panther Modern, Jake Disco, Demilson Quintao, Penumbraa, Shuhong Chen, Hongbo Men, happi nyuu nyaa, Carol Lo, Mose Sakashita, Miguel, Bandera, Gennaro Schiano, gunwoo, Ravid Freedman, Mert Seftali, Mrityunjay, Richárd Nagyfi, Timo Steiner, Henrik G Sundt, projectAnthony, Brigham Hall, Kyle Hudson, Kalila, Jef Come, Jvari Williams, Tien Tien, BIll Mangrum, owned, Janne Kytölä, SO, Richárd Nagyfi, Hector, Drexon, Claxvii 177th, Inferencer, Michael Brenner, Akkusativ, Oleg Wock, FantomBloth, Thipok Tham, Clayton Ford
[Discord] https://discord.gg/NhJZGtH
[Twitter] https://twitter.com/bycloudai
[Patreon] https://www.patreon.com/bycloud
[Music] massobeats - glisten
[Profile & Banner Art] https://twitter.com/pygm7
[Video Editor] @Askejm How RAG Turns AI Chatbots Into Something Practical](https://i.ytimg.com/vi/5Y3a61o0jFQ/mqdefault.jpg)
![The Unreasonable Effectiveness of Prompt Engineering
Check out the FREE non-technical guide for using AI in your business here: https://clickhubspot.com/fuu7
This video imma be yapping about why prompt engineering is unreasonable and everything that is a bit sus about it. The sequel of this video will probably be me roasting o1 (hopefully not)
check out my newsletter
https://mail.bycloud.ai/
Special thanks to LDJ for helping with this video
OpenAI o1
[Announcement] https://openai.com/index/introducing-openai-o1-preview/
[Blogs] https://openai.com/o1/
Claude 3.5 Sonnet
[Announcement] https://www.anthropic.com/news/claude-3-5-sonnet
[AntThinking] https://gist.github.com/dedlim/6bf6d81f77c19e20cd40594aa09e3ecd
Language Models (Mostly) Know What They Know
[Paper] https://arxiv.org/abs/2207.05221
Plan-and-Solve Prompting
[Paper] https://arxiv.org/abs/2305.04091
Llama-3.1 System Card
[Documentation] https://www.llama.com/docs/model-cards-and-prompt-formats/meta-llama-3/
Think Before You Speak
[Paper] https://arxiv.org/abs/2310.02226
Future Lens
[Paper] https://arxiv.org/abs/2311.04897
This video is supported by the kind Patrons & YouTube Members:
🙏Andrew Lescelius, alex j, Chris LeDoux, Alex Maurice, Miguilim, Deagan, FiFaŁ, Robert Zawiasa, Owen Ingraham, Daddy Wen, Tony Jimenez, Panther Modern, Jake Disco, Demilson Quintao, Penumbraa, Shuhong Chen, Hongbo Men, happi nyuu nyaa, Carol Lo, Mose Sakashita, Miguel, Bandera, Gennaro Schiano, gunwoo, Ravid Freedman, Mert Seftali, Mrityunjay, Richárd Nagyfi, Timo Steiner, Henrik G Sundt, projectAnthony, Brigham Hall, Kyle Hudson, Kalila, Jef Come, Jvari Williams, Tien Tien, BIll Mangrum, owned, Janne Kytölä, SO, Richárd Nagyfi, Hector, Drexon, Claxvii 177th, Inferencer, Michael Brenner, Akkusativ, Oleg Wock, FantomBloth, Thipok Tham, Clayton Ford, Theo, Handenon, Diego Silva, mayssam
[Discord] https://discord.gg/NhJZGtH
[Twitter] https://twitter.com/bycloudai
[Patreon] https://www.patreon.com/bycloud
[Music 1] Spirit Blossom - RomanBelov
[Music 2] Tie Me Down - PremiumMusicOdyssey
[Music 3] Dimmed Lights - PremiumMusicOdyssey
[Music 4] Wrapped in your Love - PremiumMusicOdyssey
[Profile & Banner Art] https://twitter.com/pygm7
[Video Editor] @bhargavesque
0:00 Intro
4:21 The prooompting basics
6:36 How companies make prompting works
12:11 Does how you prompt REALLY matter? The Unreasonable Effectiveness of Prompt Engineering](https://i.ytimg.com/vi/5k1zkYCuF-8/mqdefault.jpg)
![[VOD] Picking RTX4080 Super Giveaway Winner & Chill
[Discord] https://discord.gg/NhJZGtH
[Twitter] https://twitter.com/bycloudai
[Patreon] https://www.patreon.com/bycloud
My Patreon goats:
Andrew Lescelius, alex j, Chris LeDoux, Alex Maurice, Miguilim, Deagan, FiFaŁ, Daddy Wen, Tony Jimenez, Panther Modern, Jake Disco, Demilson Quintao, Shuhong Chen, Hongbo Men, happi nyuu nyaa, Carol Lo, Mose Sakashita, Miguel, Bandera, Gennaro Schiano, gunwoo, Ravid Freedman, Mert Seftali, Mrityunjay, Richárd Nagyfi, Timo Steiner, Henrik G Sundt, projectAnthony, Brigham Hall, Kyle Hudson, Kalila, Jef Come, Jvari Williams, Tien Tien, BIll Mangrum, owned, Janne Kytölä, SO, Richárd Nagyfi, Hector, Drexon [VOD] Picking RTX4080 Super Giveaway Winner & Chill](https://i.ytimg.com/vi/5mzYAmmzCMI/mqdefault.jpg)
![OpenAIs Sora: Text-to-Video AI is a World Simulator?!
check out my cool lil leaderboard website!
https://leaderboard.bycloud.ai/
Sora
[Project Page] https://openai.com/sora
[Technical Report] https://openai.com/research/video-generation-models-as-world-simulators
This video is supported by the kind Patrons & YouTube Members:
🙏Andrew Lescelius, alex j, Chris LeDoux, Alex Maurice, Miguilim, Deagan, FiFaŁ, Daddy Wen, Tony Jimenez, Panther Modern, Jake Disco, Demilson Quintao, Shuhong Chen, Hongbo Men, happi nyuu nyaa, Carol Lo, Mose Sakashita, Miguel, Bandera, Gennaro Schiano, gunwoo, Ravid Freedman, Mert Seftali, Mrityunjay, Richárd Nagyfi, Timo Steiner, Henrik G Sundt, projectAnthony, Brigham Hall, Kyle Hudson, Kalila, Jef Come, Jvari Williams, Tien Tien, BIll Mangrum, owned, Janne Kytölä, SO, Richárd Nagyfi
[Discord] https://discord.gg/NhJZGtH
[Twitter] https://twitter.com/bycloudai
[Patreon] https://www.patreon.com/bycloud
[Music] massobeats - lucid
[Profile & Banner Art] https://twitter.com/pygm7 OpenAIs Sora: Text-to-Video AI is a World Simulator?!](https://i.ytimg.com/vi/65qSQZC-kcA/mqdefault.jpg)
![Breaking Down Metas Billion Dollar LLM Blueprint [Llama-3.1 Full Breakdown]
Try out Poe now and save your $$ on multi-subscriptions! https://quora.1stcollab.com/bycloudai
check out my newsletter:
https://mail.bycloud.ai
Llama-3.1s 92 page paper is an engineering paper that most people wouldnt nearly care as much, but would be seen as the goldmine paper of LLM for any AI developers. Why is that? Lets find out what Meta researchers shared how an chungus of a model is trained and optimized.
Llama-3.1 405B
[Paper] https://arxiv.org/abs/2407.21783
This video is supported by the kind Patrons & YouTube Members:
🙏Andrew Lescelius, alex j, Chris LeDoux, Alex Maurice, Miguilim, Deagan, FiFaŁ, Robert Zawiasa, Owen Ingraham, Daddy Wen, Tony Jimenez, Panther Modern, Jake Disco, Demilson Quintao, Penumbraa, Shuhong Chen, Hongbo Men, happi nyuu nyaa, Carol Lo, Mose Sakashita, Miguel, Bandera, Gennaro Schiano, gunwoo, Ravid Freedman, Mert Seftali, Mrityunjay, Richárd Nagyfi, Timo Steiner, Henrik G Sundt, projectAnthony, Brigham Hall, Kyle Hudson, Kalila, Jef Come, Jvari Williams, Tien Tien, BIll Mangrum, owned, Janne Kytölä, SO, Richárd Nagyfi, Hector, Drexon, Claxvii 177th, Inferencer, Michael Brenner, Akkusativ, Oleg Wock, FantomBloth, Thipok Tham, Clayton Ford
[Discord] https://discord.gg/NhJZGtH
[Twitter] https://twitter.com/bycloudai
[Patreon] https://www.patreon.com/bycloud
[Music 1] massobeats - gingersweet
[Music 2] massobeats - lush
[Profile & Banner Art] https://twitter.com/pygm7
[Video Editor] Silas
0:00 Intro
2:52 model architecture
4:50 scaling law
6:39 compute & hardware optimization
10:24 Poe
11:48 Training recipe
17:49 Data mix Breaking Down Metas Billion Dollar LLM Blueprint [Llama-3.1 Full Breakdown]](https://i.ytimg.com/vi/68_BKkymYs4/mqdefault.jpg)
![Is Signal Processing The CURE For AIs ADHD?
Check out HubSpots Free ChatGPT Bundle! https://clickhubspot.com/jgv5
In this video, I will be covering the latest and the hottest paper called Differential Transformer. Will also be covering some basics about self-attention, grouped query attention, and multi-head latent attention.
check out my newsletter:
https://mail.bycloud.ai/
Attention Is All You Need
[Paper] https://arxiv.org/abs/1706.03762
GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints
[Paper] https://arxiv.org/abs/2305.13245
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
[Paper] https://arxiv.org/abs/2405.04434
Differential Transformer
[Paper] https://arxiv.org/abs/2410.05258
Flash Attention
[Paper] https://arxiv.org/abs/2205.14135
This video is supported by the kind Patrons & YouTube Members:
🙏Andrew Lescelius, Ben Shaener, Chris LeDoux, Miguilim, Deagan, FiFaŁ, Robert Zawiasa, Marcelo Ferreira, Owen Ingraham, Daddy Wen, Tony Jimenez, Panther Modern, Jake Disco, Demilson Quintao, Penumbraa, Shuhong Chen, Hongbo Men, happi nyuu nyaa, Carol Lo, Mose Sakashita, Miguel, Bandera, Gennaro Schiano, gunwoo, Ravid Freedman, Mert Seftali, Mrityunjay, Richárd Nagyfi, Timo Steiner, Henrik G Sundt, projectAnthony, Brigham Hall, Kyle Hudson, Kalila, Jef Come, Jvari Williams, Tien Tien, BIll Mangrum, owned, Janne Kytölä, SO, Richárd Nagyfi, Hector, Drexon, Claxvii 177th, Inferencer, Michael Brenner, Akkusativ, Oleg Wock, FantomBloth, Thipok Tham, Clayton Ford, Theo, Handenon, Diego Silva, mayssam, Kadhai Pesalam, Tim Schulz, jiye, Anushka
[Discord] https://discord.gg/NhJZGtH
[Twitter] https://twitter.com/bycloudai
[Patreon] https://www.patreon.com/bycloud
[Music] massobeats - glimmer
[Profile & Banner Art] https://twitter.com/pygm7
[Video Editor] @Askejm Is Signal Processing The CURE For AIs ADHD?](https://i.ytimg.com/vi/6Xy0tCidPl0/mqdefault.jpg)
![OpenAI Fired Its CEO Sam Altman, What Happened?
OpenAI Statements
https://openai.com/blog/openai-announces-leadership-transition
Sign-up for my Newsletter
https://bycloud-ai.beehiiv.com/subscribe
This video is supported by the kind Patrons & YouTube Members:
🙏Andrew Lescelius, alex j, Chris LeDoux, Alex Maurice, Miguilim, Deagan, FiFaŁ, Daddy Wen, Tony Jimenez, Panther Modern, Jake Disco, Demilson Quintao, Shuhong Chen, Hongbo Men, happi nyuu nyaa, Carol Lo, Mose Sakashita, Miguel, Bandera, Gennaro Schiano, gunwoo, Ravid Freedman, Mert Seftali, Mrityunjay, Richárd Nagyfi, Timo Steiner, Henrik G Sundt, projectAnthony, Brigham Hall, Kyle Hudson, Kalila, Jef Come, Jvari Williams, Tien Tien, BIll Mangrum, owned, Janne Kytölä, SO, Richárd Nagyfi
[Discord] https://discord.gg/NhJZGtH
[Twitter] https://twitter.com/bycloudai
[Patreon] https://www.patreon.com/bycloud
[Profile & Banner Art] https://twitter.com/pygm7 OpenAI Fired Its CEO Sam Altman, What Happened?](https://i.ytimg.com/vi/7Y1vjXkHPxk/mqdefault.jpg)
![1-Bit LLM: The Most Efficient LLM Possible?
Download Tanka today https://www.tanka.ai and enjoy 3 months of free Premium!
You can also get $20 / team for each referrals
Ive been planning for a bitnet video for the longest time, and with the release of bitnet b1.58 2B4T gave me the perfect chance to brief you on the history of 1-bit LLM! Fun fact, the major bitnet research is mostly done by the same researchers.
my latest project: Intuitive AI Academy, learn modern AI/LLMs Intuitively
https://intuitiveai.academy/
code NYNM for 50% off forever (limited to 50)
My Newsletter
https://mail.bycloud.ai/
my project: find, discover & explain AI research semantically
https://findmypapers.ai/
My Patreon
https://www.patreon.com/c/bycloud
Quantifying the Capabilities of LLMs across Scale and Precision
[Paper] https://arxiv.org/abs/2405.03146v2
BitNet: Scaling 1-bit Transformers for Large Language Models
[Paper] https://arxiv.org/abs/2310.11453v1
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
[Paper] https://arxiv.org/abs/2402.17764v1
BitNet a4.8: 4-bit Activations for 1-bit LLMs
[Paper] https://arxiv.org/abs/2411.04965v1
Efficient Construction of Model Family through Progressive Training Using Model Expansion
[Paper] https://arxiv.org/abs/2504.00623v1
BitNet b1.58 2B4T Technical Report
[Paper] https://arxiv.org/abs/2504.12285
[Web Demo] https://bitnet-demo.azurewebsites.net/
[HuggingFace] https://huggingface.co/microsoft/bitnet-b1.58-2B-4T
[Code] https://github.com/microsoft/BitNet
[Additional Recs]
T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on Edge
https://arxiv.org/abs/2407.00088v2
FBI-LLM: Scaling Up Fully Binarized LLMs from Scratch via Autoregressive Distillation
https://arxiv.org/abs/2407.07093v1
Matmul or No Matmul in the Era of 1-bit LLMs
https://arxiv.org/abs/2408.11939v2
1-bit AI Infra: Part 1.1, Fast and Lossless BitNet b1.58 Inference on CPUs
https://arxiv.org/abs/2410.16144v2
Bitnet.cpp: Efficient Edge Inference for Ternary LLMs
https://arxiv.org/abs/2502.11880v1
Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models?
https://arxiv.org/abs/2502.11895v1
(NEW!) BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs
https://arxiv.org/abs/2504.18415
(NEW!) BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation
https://arxiv.org/abs/2506.07530
Try out my new fav place to learn how to code https://scrimba.com/?via=bycloudAI
This video is supported by the kind Patrons & YouTube Members:
🙏Nous Research, Chris LeDoux, Ben Shaener, DX Research Group, Poof N Inu, Andrew Lescelius, Deagan, Robert Zawiasa, Ryszard Warzocha, Tobe2d, Louis Muk, Akkusativ, Kevin Tai, Mark Buckler, NO U, Tony Jimenez, Ângelo Fonseca, jiye, Anushka, Asad Dhamani, Binnie Yiu, Calvin Yan, Clayton Ford, Diego Silva, Etrotta, Gonzalo Fidalgo, Handenon, Hector, Jake Disco very, Michael Brenner, Nilly K, OlegWock, Daddy Wen, Shuhong Chen, Sid_Cipher, Stefan Lorenz, Sup, tantan assawade, Thipok Tham, Thomas Di Martino, Thomas Lin, Richárd Nagyfi, Paperboy, mika, Leo, Berhane-Meskel, Kadhai Pesalam, mayssam, Bill Mangrum, nyaa
[Discord] https://discord.gg/NhJZGtH
[Twitter] https://twitter.com/bycloudai
[Patreon] https://www.patreon.com/bycloud
[Business Inquiries] bycloud@smoothmedia.co
[Profile & Banner Art] https://twitter.com/pygm7
[Video Editor] Abhay
[Ko-fi] https://ko-fi.com/bycloudai 1-Bit LLM: The Most Efficient LLM Possible?](https://i.ytimg.com/vi/7hMoz9q4zv0/mqdefault.jpg)
![xLSTM: The Sequel To The Legendary LSTM
Join the waitlist now for exclusive access to the OnDemand platform: https://on-demand.io/contact
The LSTM sequel by Sepp Hochreiter is finally here, surpassing its own self by 300x and even Mamba architectures. This innovative architecture blends Scalar and Matrix LSTMs, offering a great performance increase in benchmarks and language modeling tasks. This could be big??
Check out my newsletter https://mail.bycloud.ai/
LSTM (1997)
[Paper] https://deeplearning.cs.cmu.edu/F23/document/readings/LSTM.pdf
xLSTM (2024)
[Paper] https://arxiv.org/abs/2405.04517
[unofficial resource collection] https://github.com/AI-Guru/xlstm-resources
This video is supported by the kind Patrons & YouTube Members:
🙏Andrew Lescelius, alex j, Chris LeDoux, Alex Maurice, Miguilim, Deagan, FiFaŁ, Daddy Wen, Tony Jimenez, Panther Modern, Jake Disco, Demilson Quintao, Shuhong Chen, Hongbo Men, happi nyuu nyaa, Carol Lo, Mose Sakashita, Miguel, Bandera, Gennaro Schiano, gunwoo, Ravid Freedman, Mert Seftali, Mrityunjay, Richárd Nagyfi, Timo Steiner, Henrik G Sundt, projectAnthony, Brigham Hall, Kyle Hudson, Kalila, Jef Come, Jvari Williams, Tien Tien, BIll Mangrum, owned, Janne Kytölä, SO, Richárd Nagyfi, Hector, Drexon, Claxvii 177th, Inferencer, Michael Brenner, Akkusativ, Oleg Wock, FantomBloth
[Discord] https://discord.gg/NhJZGtH
[Twitter] https://twitter.com/bycloudai
[Patreon] https://www.patreon.com/bycloud
[Music] massobeats - noon
[Profile & Banner Art] https://twitter.com/pygm7
[Video Editor] Silas xLSTM: The Sequel To The Legendary LSTM](https://i.ytimg.com/vi/7r1-4LDJDmM/mqdefault.jpg)