1. Home
  2. Detail

@sz.gui:

Guilherme.Sz
Guilherme.Sz
Open In TikTok:
Region: US
Wednesday 01 May 2024 02:07:34 GMT
54768
2348
8
560

Music

Download

No Watermark .mp4 (1.18MB) No Watermark(HD) .mp4 (1.18MB) Watermark .mp4 (0MB) Music .mp3

Comments

.escenas_depeliculas
𝕵𝖔𝖘é 𝖘𝖎𝖑𝖛𝖆 :
no sé que idioma sea, pero yo hablo español y lo entendi sin traducción, quiero aprender mas
2024-05-01 04:02:11
4
gabriel_tavares82
Gabriel Tavares :
as veses parece que não vale nd a pena, se não fazer nd não tem rendimento e se se esforçar muito tmb parece que não tem rendimento e nao da em nd!
2025-05-04 23:11:20
6
fellipe_l0pes
☆~ℱℯ𝓁𝓁𝒾𝓅ℯ~☆ :
é a msm coisa cmg.. sempre vem essa pergunta.
2026-01-29 19:24:58
2
k_i_m_2_9_3
Kim :
🥰
2025-01-07 23:47:00
0
patynao_deveriaexistir
estranha. :
as vezes me pergunto se eu devia me esforçar pra vencer a depressão sorridente
2024-07-13 03:51:57
1
aleatria4150
não e a Isa 🎸 :
realmente.
2025-10-01 20:21:24
0
To see more videos from user @sz.gui, please go to the Tikwm homepage.

Other Videos

#truyenaudiofull #truyenaudio
#truyenaudiofull #truyenaudio
trả task cho người ở nhà #quachvanthom #jgkid #thomdalab #thomdalabatvncg2026
trả task cho người ở nhà #quachvanthom #jgkid #thomdalab #thomdalabatvncg2026
#awardseason #awardseason2026
#awardseason #awardseason2026
Nobody ever wrote the code that lets ChatGPT write Python. Not one line of it. 🤯 Here's how a large language model actually gets built, step by step: 1️⃣ Data. Trillions of words of books, web pages, code and forums, then cleaned: duplicates removed, spam filtered, broken text stripped. One open dataset, FineWeb, is 15 trillion tokens of web text. 2️⃣ Tokens. The model never sees words.
Nobody ever wrote the code that lets ChatGPT write Python. Not one line of it. 🤯 Here's how a large language model actually gets built, step by step: 1️⃣ Data. Trillions of words of books, web pages, code and forums, then cleaned: duplicates removed, spam filtered, broken text stripped. One open dataset, FineWeb, is 15 trillion tokens of web text. 2️⃣ Tokens. The model never sees words. "Unbelievable" becomes 4 pieces: Un · bel · iev · able. Each piece becomes a number, and each number becomes a vector of hundreds of numbers. 3️⃣ The transformer. Stacks of layers, and inside each one, attention. In "the programmer fixed the server because it crashed", a real GPT-2 attention head sends 54% of "it"'s attention straight to "server". 4️⃣ Pre-training. One task, repeated trillions of times: predict the next token. Guess wrong, measure how wrong, nudge the weights a tiny bit downhill. Meta trained Llama 3 on up to 16,000 GPUs. 5️⃣ Post-training. A pre-trained model is just a very powerful autocomplete. Fine-tuning on good examples, human feedback and checkable rewards (did the math match? did the code pass?) turns it into an assistant. 6️⃣ Serving. A 405-billion-parameter model needs about 810 GB just for its weights. One GPU holds 80. So it gets split, compressed and batched so millions of people can use it at once. Every example in the video comes from a real model: the tokens, the attention, even the loss landscape. The weird part? Writing code, explaining physics, translating French: none of it was programmed. It all emerges from one tiny objective, repeated at enormous scale: predict what comes next, and get slightly less wrong every time. Which step surprised you most? Drop the number 👇 Save this for the next time someone calls AI "just autocomplete." #llm #artificialintelligence #machinelearning #chatgpt #techexplained

"Gel chấm mụn nào là “chân ái” cho làn da? 😍 #DCYgelchấmmụn #DaNhayCam #DaMun #GelChamMun #ChamSocDa DCY gel chấm mụn / DaDeDo / DaDeKichUng / ReviewSkincare / SkincareVietnam"


About

Legal