Загрузка видео...

Не удалось загрузить видео

На главную

Just chunking... 😭

547,457 просмотров • 1 год назад •via X (Twitter)

Комментарии: 11

Фото профиля I_AlsoShowMeat
I_AlsoShowMeat1 год назад

And these guys do a better job at directing traffic than Metro police.

Фото профиля Solar Heavy
Solar Heavy1 год назад

New single just landed! take the journey

Фото профиля BrotherFromAnotherMother
BrotherFromAnotherMother1 год назад

I truly hope someone give that man something for his efforts , doing a better job than those actually paid to do their jobs...

Фото профиля GGMe 🇿🇦🌞
GGMe 🇿🇦🌞1 год назад

This also just perfectly encapsulates the fact that the ANC has lost control, they simply don’t care or are just too inept to rescue what remains. 😢

Фото профиля ALooterContinua™
ALooterContinua™1 год назад

I hope someone gave him something. Risking his life, SAns can't drive, especially in the rain. #Taxis

Фото профиля Lindiwe Mhlaba
Lindiwe Mhlaba1 год назад

I always tip them nice

Фото профиля Aunty Debbie 🇿🇦 ♏
Aunty Debbie 🇿🇦 ♏1 год назад

Bless you.

Фото профиля Okara Maranga
Okara Maranga1 год назад

Come on South-Africans; -Someone set up a mobile money payment system with QR-code. -Let many people voluntarily send as low as only 1 rand. -He needs PPEs and these Traffic Management equipment. -Stop by and give him a hot coffee, sandwich anything! -This is better than Juvenile Deliquescence Concerned 🇰🇪Kenyan

Фото профиля Roynaldo
Roynaldo1 год назад

If everyone stops and pays him the traffic would be worse. Print him a T-shirt with a QR Code on it both sides. Drivers can open their camera and it will take them to a link to make donations. That would be an incredible gift.

Фото профиля Gordon Bauerle-Sims 🏳️‍🌈❤️🇿🇦
Gordon Bauerle-Sims 🏳️‍🌈❤️🇿🇦1 год назад

Nee man Debbie and daar begin ek 🙏🏻💫

Фото профиля Aunty Debbie 🇿🇦 ♏
Aunty Debbie 🇿🇦 ♏1 год назад

Honestly. Just couldn't contain myself. 😭

Похожие видео

Traditional chunking: cheap but dumb. ColBERT: smart but expensive. 𝗟𝗮𝘁𝗲 𝗰𝗵𝘂𝗻𝗸𝗶𝗻𝗴: the solution we've been waiting for. Here’s a quick evolution of chunking strategies: → 𝗧𝗿𝗮𝗱𝗶𝘁𝗶𝗼𝗻𝗮𝗹 𝗖𝗵𝘂𝗻𝗸𝗶𝗻𝗴 (the basics we all started with) • Token Chunking - split by token count • Sentence Chunking - split by sentence boundaries • Document-Based Chunking - split by sections/paragraphs → 𝗔𝗱𝘃𝗮𝗻𝗰𝗲𝗱 𝗖𝗵𝘂𝗻𝗸𝗶𝗻𝗴 (when things got sophisticated) • Semantic Chunking - split by meaning • LLM-Based Chunking - let the model decide But each chunking method separates text at defined points, meaning context is lost within the document from one chunk to the next. → 𝗘𝗻𝘁𝗲𝗿 𝗟𝗮𝘁𝗲 𝗖𝗵𝘂𝗻𝗸𝗶𝗻𝗴 (the game changer) Traditional approach: Chunk first → Embed each chunk separately Late chunking approach: Embed the entire document → Then chunk with context preserved 𝗪𝗵𝘆 𝗰𝗵𝗼𝗼𝘀𝗲 𝗹𝗮𝘁𝗲 𝗰𝗵𝘂𝗻𝗸𝗶𝗻𝗴? When you chunk first, each piece loses its contextual relationship to the rest of the document. It's like reading a book by randomly picking paragraphs - you miss the flow. With late chunking, every chunk maintains awareness of its neighbors because the embedding happens at the document level first. Mean pooling is done on segments AFTER the full context is embedded. Jina AI tested and saw significant improvements in retrieval quality - chunks that were previously disconnected now maintain their semantic relationships. As documents get longer and context windows expand, late chunking might just become the new standard for high-quality retrieval systems. 𝗪𝗵𝗮𝘁 𝗱𝗼 𝘆𝗼𝘂 𝗻𝗲𝗲𝗱 𝘁𝗼 𝗺𝗮𝗸𝗲 𝘁𝗵𝗶𝘀 𝘄𝗼𝗿𝗸? No modifications to your retrieval pipeline are needed. 1. Long context embedding models (8192+ tokens) 2. Chunking logic that tracks token spans 3. Less than 30 lines of code to implement All you need is to switch the order at which you chunk and embed. Embed FIRST, then chunk, not the other way around. Dive deeper into late chunking:

Femke Plantinga

125,172 просмотров • 10 месяцев назад