Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Leaked scenes from my conversation with a 3B parameter model.

HuggingModels's profile picture

Hugging Models

65,236 subscribers

68,650 Aufrufe • vor 3 Monaten •via X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

14 Kommentare

Profilbild von Ngumbahkucing
Ngumbahkucingvor 3 Monaten

3B is scary

Profilbild von petr royce
petr roycevor 3 Monaten

banger

Profilbild von RickDavis404 | AI Infra
RickDavis404 | AI Infravor 3 Monaten

...don't insult 3B parameter models like that, it was clearly over-quantized

Profilbild von theraptorlake_
theraptorlake_vor 3 Monaten

Plot twist: It's 3B active with a 50B model, it's an MOE.

Profilbild von Thomas Voelker
Thomas Voelkervor 3 Monaten

Hahah

Profilbild von chad ױ
chad ױvor 3 Monaten

Facts 🤣🤣🤣

Profilbild von Cyber Smith
Cyber Smithvor 3 Monaten

Brother user Open Source models locally and please 🥺 purchase new laptop, it's always better than that. ...

Profilbild von SubThought Corp
SubThought Corpvor 3 Monaten

When you promised your friend you'd let him be your backup singer, and knew he couldn't sing. Oaths are stronger than success.

Profilbild von Husni Marwan
Husni Marwanvor 3 Monaten

Im losing my shits dude 😂

Profilbild von DREmilare
DREmilarevor 3 Monaten

😂😂

Profilbild von Gabriel
Gabrielvor 3 Monaten

😂😂😂😂😂😂😂😂

Profilbild von Manolo LlataRoch
Manolo LlataRochvor 3 Monaten

🤣

Profilbild von PunktZero
PunktZerovor 3 Monaten

😂

Profilbild von Aditya Sri Ram
Aditya Sri Ramvor 3 Monaten

*3B model in int4 quant

Ähnliche Videos

This is from Apple's State of the Union The local model is a 3B parameter SLM that uses adapters trained for each specific feature. Diffusion model does the same thing, adapter for each style. Anything running locally or Apple's Secure Cloud is an Apple model, not OpenAI.
6:19

This is from Apple's State of the Union The local model is a 3B parameter SLM that uses adapters trained for each specific feature. Diffusion model does the same thing, adapter for each style. Anything running locally or Apple's Secure Cloud is an Apple model, not OpenAI.

Max Weinbach

2,648,758 Aufrufe • vor 2 Jahren

ten years with one of my absolute favourite scenes from skam. Can not overstate how important this conversation was
3:20

ten years with one of my absolute favourite scenes from skam. Can not overstate how important this conversation was

jo🌞🏒

450,226 Aufrufe • vor 10 Tagen

Changing mouth paramaters on MOU Model to flow with your lips better. IT'S ME I AM BACK WITH MY HYPERFIXATION OF PARAMETER PERFECTION .
1:59

Changing mouth paramaters on MOU Model to flow with your lips better. IT'S ME I AM BACK WITH MY HYPERFIXATION OF PARAMETER PERFECTION .

Eerithu

23,336 Aufrufe • vor 19 Tagen

Leaked scenes from Harvard University... .
0:53

Leaked scenes from Harvard University... .

చార్వాక

32,795 Aufrufe • vor 9 Monaten

Leaked scenes from Spy training :
0:33

Leaked scenes from Spy training :

DEVENDRA cυLƚ

69,647 Aufrufe • vor 9 Monaten

Leaked conversation from the White House! 😳
0:24

Leaked conversation from the White House! 😳

Political Kida

44,896 Aufrufe • vor 10 Monaten

TENCENT casually dropping a 13bn parameter open sourced video model WITH weights 🩵 Looks unreal and can't wait to test it
1:23

TENCENT casually dropping a 13bn parameter open sourced video model WITH weights 🩵 Looks unreal and can't wait to test it

A.I.Warper

156,471 Aufrufe • vor 1 Jahr

GROK 5. the first 7 trillion parameter model
1:24

GROK 5. the first 7 trillion parameter model

🍓🍓🍓

39,839 Aufrufe • vor 10 Monaten

We built 10 live-camera demos for d1-3B, from gesture-controlled games to content moderation, with one forward pass per frame. In collaboration with NVIDIA Robotics, we also show d1-3B navigating an environment in Isaac Sim, with the model served on a Jetson in a hardware-in-the-loop setup. 5/
0:42

We built 10 live-camera demos for d1-3B, from gesture-controlled games to content moderation, with one forward pass per frame. In collaboration with NVIDIA Robotics, we also show d1-3B navigating an environment in Isaac Sim, with the model served on a Jetson in a hardware-in-the-loop setup. 5/

Liquid AI

19,037 Aufrufe • vor 1 Monat

WebGPU is INSANE! 🤯 Here's a 24B parameter model running locally in a web browser, at a blazing ~50 tokens/second on my M4 Max. ⚡️ It's the largest model we've ever run with Transformers.js... and we're not stopping here. Big announcement soon.
1:05

WebGPU is INSANE! 🤯 Here's a 24B parameter model running locally in a web browser, at a blazing ~50 tokens/second on my M4 Max. ⚡️ It's the largest model we've ever run with Transformers.js... and we're not stopping here. Big announcement soon.

Xenova

36,309 Aufrufe • vor 7 Monaten

ELON MUSK: "Grok 5 will be the largest model, a 6 trillion parameter model, whereas Grok 3 and 4 are based on a 3 trillion parameter model. Moreover, the 6 trillion parameters will have a much higher intelligence density per gigabyte. Its really going to feel Sentient."
2:14

ELON MUSK: "Grok 5 will be the largest model, a 6 trillion parameter model, whereas Grok 3 and 4 are based on a 3 trillion parameter model. Moreover, the 6 trillion parameters will have a much higher intelligence density per gigabyte. Its really going to feel Sentient."

DogeDesigner

322,452 Aufrufe • vor 1 Jahr

Leaked scenes from SRH dressing room last night 🥵
0:30

Leaked scenes from SRH dressing room last night 🥵

Kakarot⚡🇮🇳🦅

24,817 Aufrufe • vor 7 Monaten

Leaked from Asif's phone - Plan to demolish Dhanmondi 32.. Listen to Pinky and Advisor Asif's leaked phone conversation..
2:36

Leaked from Asif's phone - Plan to demolish Dhanmondi 32.. Listen to Pinky and Advisor Asif's leaked phone conversation..

BM Jahid Hasan

45,357 Aufrufe • vor 1 Jahr

Don't be a victim. This is a clip from my conversation with Piers Morgan
1:04

Don't be a victim. This is a clip from my conversation with Piers Morgan

Robert Greene

105,276 Aufrufe • vor 1 Jahr

🚨 ANTHROPIC TRIED TO BAN HIS GITHUB Chinese guy published 70B parameter LLM, 20,000 starts on Github + a lawsuit from big AI companies Here's what it does: > runs on Python > even shitty mac or pc is enough > flat memory > loads a model layer by layer > 100% local This model can close 100% needs of most businesses, which would pay $3,000/a month for a trained version. It needs just 4 gb of GPU, so using this technology my gaming pc with 12 gb GPU will run 200B parameter model with ease Github link is below. Why you should go local too.
0:41

🚨 ANTHROPIC TRIED TO BAN HIS GITHUB Chinese guy published 70B parameter LLM, 20,000 starts on Github + a lawsuit from big AI companies Here's what it does: > runs on Python > even shitty mac or pc is enough > flat memory > loads a model layer by layer > 100% local This model can close 100% needs of most businesses, which would pay $3,000/a month for a trained version. It needs just 4 gb of GPU, so using this technology my gaming pc with 12 gb GPU will run 200B parameter model with ease Github link is below. Why you should go local too.

Milady

492,687 Aufrufe • vor 4 Monaten

How can a 30B-parameter model activate just 3B parameters per token and still draw on the full model’s capacity? Learn how dense and MoE models use parameters differently, and what that means for throughput, memory and serving complexity. Check out our new technical explainer:
1:05

How can a 30B-parameter model activate just 3B parameters per token and still draw on the full model’s capacity? Learn how dense and MoE models use parameters differently, and what that means for throughput, memory and serving complexity. Check out our new technical explainer:

NVIDIA AI

19,191 Aufrufe • vor 1 Monat

Behind the scenes leaked from the sets of #Spirit 🔥
0:36

Sensitive content

Behind the scenes leaked from the sets of #Spirit 🔥

A.J7🇵🇱

278,124 Aufrufe • vor 2 Monaten