Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Base models are insanely powerful, and far more creative than instruction-tuned models like GPT-4 and Claude. But few people have actually had a chance to use them. That changes today. I've built a playground that allows you to interact with Llama 3.1 405B Base:

Matt Shumer

367,707 subscribers

117,782 görüntüleme • 1 yıl önce •via X (Twitter)

Eğitim Sanat Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

11 Yorum

Matt Shumer profil fotoğrafı

Matt Shumer1 yıl önce

Just add your OpenRouter API key, and you're good to go. It takes a bit of practice to get the hang of it (lean on few-shot prompting!) but once you figure it out, you'll be able to get very creative results that instruct models don't enable. Try here:

Synaptic Quantica profil fotoğrafı

Synaptic Quantica1 yıl önce

you know what would be epic? To have the raw base gpt4 without any safety nor any fine-tune

Matt Shumer profil fotoğrafı

Matt Shumer1 yıl önce

I used it during the testing phase — was an amazing experience L3.1 405B feels very similar

MattVidPro AI profil fotoğrafı

MattVidPro AI1 yıl önce

I love base models

anas profil fotoğrafı

anas1 yıl önce

The app was made with Claude sonnet 3.5 ?

Matt Shumer profil fotoğrafı

Matt Shumer1 yıl önce

Of course!

Jasper profil fotoğrafı

Jasper1 yıl önce

Great to see that you use the base model powered by us @hyperbolic_labs on @OpenRouterAI 🤘

Matt Shumer profil fotoğrafı

Matt Shumer1 yıl önce

@hyperbolic_labs @OpenRouterAI Thanks for hosting it!!

Hyperbolic profil fotoğrafı

Hyperbolic1 yıl önce

Glad to see you're enjoying our base model! We are considering providing Llama 3.1 405B Base *at bf16*... should we do it? 👀

Michael profil fotoğrafı

Michael1 yıl önce

I missed green text so much. Thanks Matt

Matt Shumer profil fotoğrafı

Matt Shumer1 yıl önce

Same. Green text is making a comeback

Benzer Videolar

Exciting day today as Meta launches its new Llama 3.1 models and they’re available in Bedrock immediately. Llama 3.1 is a substantial step forward and the models (highlighted by the powerful 405B model) are impressive and powerful. Customers are gonna love these high performance models. Giddy up!

Exciting day today as Meta launches its new Llama 3.1 models and they’re available in Bedrock immediately. Llama 3.1 is a substantial step forward and the models (highlighted by the powerful 405B model) are impressive and powerful. Customers are gonna love these high performance models. Giddy up!

Andy Jassy

45,000 görüntüleme • 1 yıl önce

You can now try Llama 3.1 405B for free (link below)! This is the largest open-source model out there, and for the first time, an open model is competitive with closed models. This time around, Meta did something new: Llama 3.1 has a license that allows developers to use it to enhance other models. For the first time, you can distill Llama 3.1 405B's capabilities into a smaller, more practical model for your use case. First, here is the link where you can play with Llama 3.1 for free: The model is hosted in Tune Studio, an end-to-end platform for developing applications using Large Language Models. They are sponsoring this post. Take a look at the attached video. It will show you how you can fine-tune a simple model using Llama 3.1 without leaving the platform: 1. You can create an empty dataset 2. Use the playground to generate and record interactions with Llama 3.1 3. Modify the dataset directly using the playground 4. Export the data and fine-tune a smaller model Fast and easy! As long as you have a web browser, you can start experimenting with fine-tuning and Llama 3.1. That's all it takes!

You can now try Llama 3.1 405B for free (link below)! This is the largest open-source model out there, and for the first time, an open model is competitive with closed models. This time around, Meta did something new: Llama 3.1 has a license that allows developers to use it to enhance other models. For the first time, you can distill Llama 3.1 405B's capabilities into a smaller, more practical model for your use case. First, here is the link where you can play with Llama 3.1 for free: The model is hosted in Tune Studio, an end-to-end platform for developing applications using Large Language Models. They are sponsoring this post. Take a look at the attached video. It will show you how you can fine-tune a simple model using Llama 3.1 without leaving the platform: 1. You can create an empty dataset 2. Use the playground to generate and record interactions with Llama 3.1 3. Modify the dataset directly using the playground 4. Export the data and fine-tune a smaller model Fast and easy! As long as you have a web browser, you can start experimenting with fine-tuning and Llama 3.1. That's all it takes!

Santiago

55,609 görüntüleme • 1 yıl önce

Starting today, open source is leading the way. Introducing Llama 3.1: Our most capable models yet. Today we’re releasing a collection of new Llama 3.1 models including our long awaited 405B. These models deliver improved reasoning capabilities, a larger 128K token context window and improved support for 8 languages among other improvements. Llama 3.1 405B rivals leading closed source models on state-of-the-art capabilities across a range of tasks in general knowledge, steerability, math, tool use and multilingual translation. The models are available to download now directly from Meta or Hugging Face. With today’s release the ecosystem is also ready to go with 25+ partners rolling out our latest models — including Amazon Web Services, NVIDIA, Databricks, Groq Inc, Dell Technologies, Microsoft Azure and Google Cloud ready on day one. More details in the full announcement ➡️ Download Llama 3.1 models ➡️ With these releases we’re setting the stage for unprecedented new opportunities and we can’t wait to see the innovation our newest models will unlock across all levels of the AI community.

Starting today, open source is leading the way. Introducing Llama 3.1: Our most capable models yet. Today we’re releasing a collection of new Llama 3.1 models including our long awaited 405B. These models deliver improved reasoning capabilities, a larger 128K token context window and improved support for 8 languages among other improvements. Llama 3.1 405B rivals leading closed source models on state-of-the-art capabilities across a range of tasks in general knowledge, steerability, math, tool use and multilingual translation. The models are available to download now directly from Meta or Hugging Face. With today’s release the ecosystem is also ready to go with 25+ partners rolling out our latest models — including Amazon Web Services, NVIDIA, Databricks, Groq Inc, Dell Technologies, Microsoft Azure and Google Cloud ready on day one. More details in the full announcement ➡️ Download Llama 3.1 models ➡️ With these releases we’re setting the stage for unprecedented new opportunities and we can’t wait to see the innovation our newest models will unlock across all levels of the AI community.

AI at Meta

1,268,534 görüntüleme • 1 yıl önce

Introducing Stack Overflow searches with GPT-4o in VSCode This new feature allows you to use the capabilities of /StackOverflow find related posts ensuring a far more accurate answer to your question. There's no waiting list! 🤩 You can use this today! All you have to do is install the CodeGPT extension in VSCode and use OpenAI models (GPT-4o)

Introducing Stack Overflow searches with GPT-4o in VSCode This new feature allows you to use the capabilities of /StackOverflow find related posts ensuring a far more accurate answer to your question. There's no waiting list! 🤩 You can use this today! All you have to do is install the CodeGPT extension in VSCode and use OpenAI models (GPT-4o)

Daniel San

20,105 görüntüleme • 1 yıl önce

Running multi agents on open source models has always been a hit or miss until... Llama 3.1 on Groq Inc with 405b and 70b

Running multi agents on open source models has always been a hit or miss until... Llama 3.1 on Groq Inc with 405b and 70b

FlowiseAI

48,208 görüntüleme • 1 yıl önce

"One of the big things that we're focusing on with the Base app, and one of the reasons why people are coming to use it, is that when you post on Base, you actually earn." - jesse.base.eth on TBPN

"One of the big things that we're focusing on with the Base app, and one of the reasons why people are coming to use it, is that when you post on Base, you actually earn." - jesse.base.eth on TBPN

Base

100,600 görüntüleme • 11 ay önce

As models get smarter and more capable, you will get diminishing returns prompting them yourself. Enter "Orchestrate" a powerful new workflow in Repo Prompt that allows you to combine the strengths of GPT 5.5 and Opus 4.7 in ways no other tool makes possible.

As models get smarter and more capable, you will get diminishing returns prompting them yourself. Enter "Orchestrate" a powerful new workflow in Repo Prompt that allows you to combine the strengths of GPT 5.5 and Opus 4.7 in ways no other tool makes possible.

eric provencher

67,148 görüntüleme • 2 ay önce

meta just released llama 3.1 you can now build & deploy a quick chatbot that learns more and more about you as you talk to it. in literally less than 10 minutes. here's how. there's no better time to build and ship stuff. these open models are incredible!

meta just released llama 3.1 you can now build & deploy a quick chatbot that learns more and more about you as you talk to it. in literally less than 10 minutes. here's how. there's no better time to build and ship stuff. these open models are incredible!

Dhravya Shah

409,226 görüntüleme • 1 yıl önce

Introducing LlamaCoder! An open source Claude Artifacts app that can generate full React apps and components with Llama 3.1 405B. 100% free and open source.

Introducing LlamaCoder! An open source Claude Artifacts app that can generate full React apps and components with Llama 3.1 405B. 100% free and open source.

Hassan

501,419 görüntüleme • 1 yıl önce

New short course: Prompt Engineering with Llama 2, built in collaboration with Meta AI at Meta, and taught by Amit Sangani! Meta's Llama 2 has been game-changing for AI. Building with open source lets you control your own data, scrutinize errors, update (or not) the models as you please, and work alongside the global community advancing open models. Llama isn't a single model, it's a collection of models. In this course, you'll: - Learn the differences between different Llama 2 flavors, and when to use each. - Prompt the Llama chat models -- you'll also see how Llama's instruction tags work -- so they can help you with day-to-day tasks, like writing or summarization. - Use advanced prompting, like few-shot prompting for classification, and chain-of-thought prompting for solving logic problems. - Use specialized models in the Llama collection for specific tasks, like Code Llama to help you write, analyze, and improve code, and Llama Guard, which checks prompts and model responses for harmful content. The course also touches on how to run Llama 2 locally on your own computer. I hope you’ll take this course and try out these powerful, open models!

New short course: Prompt Engineering with Llama 2, built in collaboration with Meta AI at Meta, and taught by Amit Sangani! Meta's Llama 2 has been game-changing for AI. Building with open source lets you control your own data, scrutinize errors, update (or not) the models as you please, and work alongside the global community advancing open models. Llama isn't a single model, it's a collection of models. In this course, you'll: - Learn the differences between different Llama 2 flavors, and when to use each. - Prompt the Llama chat models -- you'll also see how Llama's instruction tags work -- so they can help you with day-to-day tasks, like writing or summarization. - Use advanced prompting, like few-shot prompting for classification, and chain-of-thought prompting for solving logic problems. - Use specialized models in the Llama collection for specific tasks, like Code Llama to help you write, analyze, and improve code, and Llama Guard, which checks prompts and model responses for harmful content. The course also touches on how to run Llama 2 locally on your own computer. I hope you’ll take this course and try out these powerful, open models!

Andrew Ng

162,798 görüntüleme • 2 yıl önce

Fei-Fei Li says we're not far from a "ChatGPT moment" for world models ChatGPT succeeded because GPT-3.5 was powerful enough to go viral when productized "world models need that same foundation first" Once these models are productized and widely accessible, that will be a ChatGPT moment

Fei-Fei Li says we're not far from a "ChatGPT moment" for world models ChatGPT succeeded because GPT-3.5 was powerful enough to go viral when productized "world models need that same foundation first" Once these models are productized and widely accessible, that will be a ChatGPT moment

Haider.

112,971 görüntüleme • 6 ay önce

The two bad things about supporting arbitrary 3d models as characters is that I have to actually learn how to use the unity animator, and character sprites interact incredibly poorly with other 3d geometry that gets really close to them.

The two bad things about supporting arbitrary 3d models as characters is that I have to actually learn how to use the unity animator, and character sprites interact incredibly poorly with other 3d geometry that gets really close to them.

TheDoddlerRO

25,199 görüntüleme • 3 ay önce

“You Will Pray To Fall Victim To Bandits Than To Be Taken By Tiger Base Officers Because You Have a Better Chance Of Coming Out Alive With Bandits Than From Tiger Base. Only The Governor, IG Of Police, And President Of Nigeria Can Save You If Detained In Tiger Base. I’m Glad That People Are Now Speaking Out About The Atrocities Of Tiger Base.” – Man

“You Will Pray To Fall Victim To Bandits Than To Be Taken By Tiger Base Officers Because You Have a Better Chance Of Coming Out Alive With Bandits Than From Tiger Base. Only The Governor, IG Of Police, And President Of Nigeria Can Save You If Detained In Tiger Base. I’m Glad That People Are Now Speaking Out About The Atrocities Of Tiger Base.” – Man

Somto Okonkwo

15,842 görüntüleme • 6 ay önce

In between major AI model breakthroughs, new models still ship, but they’re not fundamentally expanding what you can do with them. Braintrust CEO Ankur Goyal says that’s exactly when open source starts to surge: "When new models come out, people forget about open source and forget about economics because it changes fundamentally what you can do." "Programming is a good example. The workflow today is completely different than it was a year ago. If you tried to use models from a year ago today, you wouldn't be able to do crazy stuff like OpenClaw or whatever people are building nowadays." "When models don't change at that speed, people optimize the performance on the use cases that they have." "If you look at usage on our platform, almost half the token usage is coming from open source models from a very small number of companies that have figured out how to optimize use cases really well."

In between major AI model breakthroughs, new models still ship, but they’re not fundamentally expanding what you can do with them. Braintrust CEO Ankur Goyal says that’s exactly when open source starts to surge: "When new models come out, people forget about open source and forget about economics because it changes fundamentally what you can do." "Programming is a good example. The workflow today is completely different than it was a year ago. If you tried to use models from a year ago today, you wouldn't be able to do crazy stuff like OpenClaw or whatever people are building nowadays." "When models don't change at that speed, people optimize the performance on the use cases that they have." "If you look at usage on our platform, almost half the token usage is coming from open source models from a very small number of companies that have figured out how to optimize use cases really well."

TBPN

16,294 görüntüleme • 4 ay önce

This is wild! Llama 3.1 405B Instruct finally solves a famous math puzzle that was originally posted on /LocalLlama. To the best of my knowledge, every model (including Claude 3.5 Sonnet and GPT-4o) fails at this task. A longer video coming soon!

This is wild! Llama 3.1 405B Instruct finally solves a famous math puzzle that was originally posted on /LocalLlama. To the best of my knowledge, every model (including Claude 3.5 Sonnet and GPT-4o) fails at this task. A longer video coming soon!

elvis

52,546 görüntüleme • 1 yıl önce

This is the fastest I've seen Llama 3.3 running anywhere! Llama 3.3 70B running at 652 t/s is lightning fast. And if you want Llama 3.1, here are the speeds I was able to get: • Llama 3.1 8B: 1006 t/s • Llama 3.1 70B: 709 t/s • Llama 3.1 405B: 206 t/s (You can access all of these models for free! See the link below.) This speed is incredible, but the interesting part is what's happening behind the scenes: These models aren't running on a GPU! In this video, I'm using the SambaNova cloud to access these models. They built a custom chip (SN40L) optimized for AI workflows. A single SN40L chip can hold hundreds of models (trillions of parameters) in memory! The speed alone is a huge deal, but the big advantage is for agentic workflows running multiple specialized models. A GPU can only host a single model and switch (unload and load) to a different model if necessary. An SN40L, on the other hand, can host every model at once, making it much faster. Here is the video where you can see how fast these chips are:

This is the fastest I've seen Llama 3.3 running anywhere! Llama 3.3 70B running at 652 t/s is lightning fast. And if you want Llama 3.1, here are the speeds I was able to get: • Llama 3.1 8B: 1006 t/s • Llama 3.1 70B: 709 t/s • Llama 3.1 405B: 206 t/s (You can access all of these models for free! See the link below.) This speed is incredible, but the interesting part is what's happening behind the scenes: These models aren't running on a GPU! In this video, I'm using the SambaNova cloud to access these models. They built a custom chip (SN40L) optimized for AI workflows. A single SN40L chip can hold hundreds of models (trillions of parameters) in memory! The speed alone is a huge deal, but the big advantage is for agentic workflows running multiple specialized models. A GPU can only host a single model and switch (unload and load) to a different model if necessary. An SN40L, on the other hand, can host every model at once, making it much faster. Here is the video where you can see how fast these chips are:

Santiago

97,505 görüntüleme • 1 yıl önce

We've been limited to Claude Desktop and IDEs like Cursor for MCP... until now. ⚡️ We shipped Groq Desktop, a new MCP host that's insanely fast. You can now give models like Llama 4 Scout and Qwen QwQ 32B the ability to instantly read PDFs, connect to Slack, and so much more.

We've been limited to Claude Desktop and IDEs like Cursor for MCP... until now. ⚡️ We shipped Groq Desktop, a new MCP host that's insanely fast. You can now give models like Llama 4 Scout and Qwen QwQ 32B the ability to instantly read PDFs, connect to Slack, and so much more.

Hatice Ozen

159,568 görüntüleme • 1 yıl önce

Sam Altman "Internally, we've reached GPT-4.5, and getting to GPT-5.5 won't require 100x more compute" - progress in reasoning models and RL techniques have greatly improved compute efficiency - it allows smaller models like internal GPT-4.5 to achieve GPT-6 level performance without requiring 100x more computing power

Sam Altman "Internally, we've reached GPT-4.5, and getting to GPT-5.5 won't require 100x more compute" - progress in reasoning models and RL techniques have greatly improved compute efficiency - it allows smaller models like internal GPT-4.5 to achieve GPT-6 level performance without requiring 100x more computing power

Haider.

344,581 görüntüleme • 1 yıl önce

NEW: OnlyFans CEO Keily Blair says OF is important because it allows "creators to connect with their fanbase" and "express themselves." Lmao. "[OF] enables creators to connect with their fan base, express themselves in a free way, and to really grow their fan base and to enable them to improve their global reach for fans." "It enables them to interact ... and to really experience that creator fan dynamic, which is very different to other social media platforms, which are much more broadcast." "So ultimately people are ready to pay, to interact with creators, and to pay to receive media content."

NEW: OnlyFans CEO Keily Blair says OF is important because it allows "creators to connect with their fanbase" and "express themselves." Lmao. "[OF] enables creators to connect with their fan base, express themselves in a free way, and to really grow their fan base and to enable them to improve their global reach for fans." "It enables them to interact ... and to really experience that creator fan dynamic, which is very different to other social media platforms, which are much more broadcast." "So ultimately people are ready to pay, to interact with creators, and to pay to receive media content."

Collin Rugg

930,272 görüntüleme • 1 yıl önce

Introducing Orgo, Computers for AI Agents. AI apps today are constrained to a chat interface and text responses. With Orgo, you can give a model like GPT access to a full computer. Orgo provides full desktop environments which can be controlled by AI models like GPT and Claude. Available now for developers.

Introducing Orgo, Computers for AI Agents. AI apps today are constrained to a chat interface and text responses. With Orgo, you can give a model like GPT access to a full computer. Orgo provides full desktop environments which can be controlled by AI models like GPT and Claude. Available now for developers.

Spencer Kinney

279,643 görüntüleme • 11 ay önce