Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

We just shipped support for tool use and JSON mode for DeepSeek R1 Distil-Llama 70B on Groq Inc. 🛠️ The coolest part is that our API now has a `reasoning_format` parameter that lets you control how the model outputs its thought process.

ozenhati's profile picture

Hatice Ozen

4,750 subscribers

43,225 Aufrufe • vor 1 Jahr •via X (Twitter)

BildungWissenschaft & TechnologieNachrichten & Politik
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

We just launched support for DeepSeek (DeepSeek) R1 and V3 in Agent Mode! - Switch to Agent Mode by pressing CMD-I - Click on the model name in the prompt Hosted by Fireworks AI in the US.
0:16

We just launched support for DeepSeek (DeepSeek) R1 and V3 in Agent Mode! - Switch to Agent Mode by pressing CMD-I - Click on the model name in the prompt Hosted by Fireworks AI in the US.

Warp

14,154 Aufrufe • vor 1 Jahr

DeepSeek R1 is *the* best model available right now. It's at the level of o1, but you can use it for free, and it's much faster. A huge leap forward that nobody saw coming. No wonder so many people are throwing tantrums online trying to discredit the Chinese students who built this. You can use DeepSeek in Visual Studio Code right now: 1. Install the Qodo Gen AI extension 2. Select DeepSeek R1 from their list of models The Qodo team is hosting DeepSeek on their servers, so none of your data will go to China. I've been building a Tetris game using DeepSeek, and this is the most impressive model I've seen so far.
0:17

DeepSeek R1 is *the* best model available right now. It's at the level of o1, but you can use it for free, and it's much faster. A huge leap forward that nobody saw coming. No wonder so many people are throwing tantrums online trying to discredit the Chinese students who built this. You can use DeepSeek in Visual Studio Code right now: 1. Install the Qodo Gen AI extension 2. Select DeepSeek R1 from their list of models The Qodo team is hosting DeepSeek on their servers, so none of your data will go to China. I've been building a Tetris game using DeepSeek, and this is the most impressive model I've seen so far.

Santiago

1,224,059 Aufrufe • vor 1 Jahr

We are thrilled to be a launch partner for Meta Llama 3. Experience Llama 3 now at up to 350 tokens per second for Llama 3 8B and up to 150 tokens per second for Llama 3 70B, running in full FP16 precision on the Together API! 🤯
0:10

We are thrilled to be a launch partner for Meta Llama 3. Experience Llama 3 now at up to 350 tokens per second for Llama 3 8B and up to 150 tokens per second for Llama 3 70B, running in full FP16 precision on the Together API! 🤯

Together AI

88,229 Aufrufe • vor 2 Jahren

Huge step for people who want to integrate video production as part of a workflow: $ pixverse create video --prompt "a parisian scene during a rainy day." You can now run the PixVerse CLI or integrate with their API: • JSON outputs • Asynchronous generation • Really easy debugging and task tracking • Deterministic exit codes The terminal changes how you use the product entirely.
0:12

Huge step for people who want to integrate video production as part of a workflow: $ pixverse create video --prompt "a parisian scene during a rainy day." You can now run the PixVerse CLI or integrate with their API: • JSON outputs • Asynchronous generation • Really easy debugging and task tracking • Deterministic exit codes The terminal changes how you use the product entirely.

Santiago

14,237 Aufrufe • vor 3 Monaten

Tiny Recursive Models: A tiny 7M parameter model that recursively refines its answer beats LLMs 100x larger on hard puzzles like ARC-AGI We independently reproduced the paper, corroborated results, and released the weights + API access for those looking to benchmark it 🔍
0:19

Tiny Recursive Models: A tiny 7M parameter model that recursively refines its answer beats LLMs 100x larger on hard puzzles like ARC-AGI We independently reproduced the paper, corroborated results, and released the weights + API access for those looking to benchmark it 🔍

alphaXiv

52,395 Aufrufe • vor 8 Monaten

Currently learning how Archaludon's Pokemon model works and it has way more stuff going on that I thought, didn't expect it to use a different model for Electro Shot
0:18

Currently learning how Archaludon's Pokemon model works and it has way more stuff going on that I thought, didn't expect it to use a different model for Electro Shot

Yisuno ⚝ | MEGA ENJOYER

535,789 Aufrufe • vor 1 Jahr

Happy Friday! We just put DeepSeek-V4-Pro up on It’s the world’s largest open source model at 1.6T parameters, and you can run it for free running on NVIDIA Blackwell GPUs. Try the NVIDIA NIM API →
0:18

Happy Friday! We just put DeepSeek-V4-Pro up on It’s the world’s largest open source model at 1.6T parameters, and you can run it for free running on NVIDIA Blackwell GPUs. Try the NVIDIA NIM API →

NVIDIA AI

204,093 Aufrufe • vor 2 Monaten

It's over. OpenAI just crushed it. We have their o3-level open-source model running on Groq Inc at 500 tokens per second. Watch it build an entire SaaS app in just a few seconds. This is the new standard. Why the hell would you use anything else??
0:16

It's over. OpenAI just crushed it. We have their o3-level open-source model running on Groq Inc at 500 tokens per second. Watch it build an entire SaaS app in just a few seconds. This is the new standard. Why the hell would you use anything else??

Matt Shumer

498,609 Aufrufe • vor 11 Monaten

The only tool we use for animation is Rive. Our agency relies entirely on Rive for its features, and we believe it's the #1 solution for this type of animation. Rive animations are lightweight and high-performance too.
0:11

The only tool we use for animation is Rive. Our agency relies entirely on Rive for its features, and we believe it's the #1 solution for this type of animation. Rive animations are lightweight and high-performance too.

Praha

44,326 Aufrufe • vor 6 Monaten

I just got Codex to reverse engineer the Control+M speech-to-text mode in the Codex app and build a Mac app that lets you run it anywhere. The demo is me making this tweet right now.
0:16

I just got Codex to reverse engineer the Control+M speech-to-text mode in the Codex app and build a Mac app that lets you run it anywhere. The demo is me making this tweet right now.

Anthony Kroeger

141,513 Aufrufe • vor 2 Monaten

kubectx v0.11 now ships with a 'readonly' mode for kubectl (and any tool that uses k8s API) and forbids any calls that mutate state. it basically runs a temporary reverse proxy to block these requests during the lifespan of the shell. here's a demo:
0:12

kubectx v0.11 now ships with a 'readonly' mode for kubectl (and any tool that uses k8s API) and forbids any calls that mutate state. it basically runs a temporary reverse proxy to block these requests during the lifespan of the shell. here's a demo:

ahmet alp balkan

31,211 Aufrufe • vor 3 Monaten

Today we introduced AlphaGenome, a new tool that can more comprehensively predict the impact of single variants or mutations in DNA 🧬 How, you ask? 🤔 tldr; Our AlphaGenome model takes a long DNA sequence as input, processes that data, and predicts thousands of molecular properties by characterizing its regulatory activity. For the full read ➡️
0:18

Today we introduced AlphaGenome, a new tool that can more comprehensively predict the impact of single variants or mutations in DNA 🧬 How, you ask? 🤔 tldr; Our AlphaGenome model takes a long DNA sequence as input, processes that data, and predicts thousands of molecular properties by characterizing its regulatory activity. For the full read ➡️

Google AI

83,048 Aufrufe • vor 1 Jahr

First steps for a specialized DeepSeek v4 Flash inference engine focused on inference quality / stability at different quantizations, with networked API that is batching capable. This is the 2 bit quants model running on my M3 Max 128GB.
0:12

First steps for a specialized DeepSeek v4 Flash inference engine focused on inference quality / stability at different quantizations, with networked API that is batching capable. This is the 2 bit quants model running on my M3 Max 128GB.

antirez

14,176 Aufrufe • vor 2 Monaten

In January, we lost 15 cows to January Disease. The dip in Gutu near our homestead is about 10kms away, so the lads on the ground often didn't bother going. Ticks where the cause. I built this app so that I could micro manage all our remaining 35 cows as I was just too removed at the time. Now that I'm here, this tool still is invaluable. I've tided it up and now its available for everyone, free to use. If you're in the diaspora or on the ground, get rid of the spread sheets and whatsapp message scrolling and get in total control of your herd! live now on
0:11

In January, we lost 15 cows to January Disease. The dip in Gutu near our homestead is about 10kms away, so the lads on the ground often didn't bother going. Ticks where the cause. I built this app so that I could micro manage all our remaining 35 cows as I was just too removed at the time. Now that I'm here, this tool still is invaluable. I've tided it up and now its available for everyone, free to use. If you're in the diaspora or on the ground, get rid of the spread sheets and whatsapp message scrolling and get in total control of your herd! live now on

K

30,582 Aufrufe • vor 8 Monaten

Today we’re releasing Code Llama, a large language model built on top of Llama 2, fine-tuned for coding & state-of-the-art for publicly available coding tools. Keeping with our open approach, Code Llama is publicly-available now for both research & commercial use. More ⬇️
0:14

Today we’re releasing Code Llama, a large language model built on top of Llama 2, fine-tuned for coding & state-of-the-art for publicly available coding tools. Keeping with our open approach, Code Llama is publicly-available now for both research & commercial use. More ⬇️

AI at Meta

1,004,918 Aufrufe • vor 2 Jahren

Today—we evolve BRĒZ ❤️‍🔥 Our mission is to reduce human suffering and maximize human potential through a better beverage. We further that now, with two major changes: 1. Prices have dropped—permanently. We often hear how much our customers love BRĒZ but the price makes it just a bit too out of reach - with the support of our community we’ve reached some scale, and with it we’ve unlocked savings that we’re officially passing on to our customers. 2. Custom bundles are live. You can now build exactly what you want, how you want it, and save even more in the process. The goal with these changes is simple, serve our customers by making BRĒZ more accessible, more shareable, and more personalized. Thank you all for your support throughout this journey — all changes live now on 🤘
0:12

Today—we evolve BRĒZ ❤️‍🔥 Our mission is to reduce human suffering and maximize human potential through a better beverage. We further that now, with two major changes: 1. Prices have dropped—permanently. We often hear how much our customers love BRĒZ but the price makes it just a bit too out of reach - with the support of our community we’ve reached some scale, and with it we’ve unlocked savings that we’re officially passing on to our customers. 2. Custom bundles are live. You can now build exactly what you want, how you want it, and save even more in the process. The goal with these changes is simple, serve our customers by making BRĒZ more accessible, more shareable, and more personalized. Thank you all for your support throughout this journey — all changes live now on 🤘

Aaron Nosbisch

35,841 Aufrufe • vor 1 Jahr

Testing SCAIL-2, an open source model for motion transfer. I wanted to see how it can handle driving videos with fast, dynamic movement. The part that really impressed me was how the model retained details from the input character's outfit (especially the straps on the shorts). I attached the input character below for you to compare against. The model also has a replacement mode that swaps the character into the driving video's scene, but here I used animation mode, which keeps the reference image's scene instead.
0:18

Testing SCAIL-2, an open source model for motion transfer. I wanted to see how it can handle driving videos with fast, dynamic movement. The part that really impressed me was how the model retained details from the input character's outfit (especially the straps on the shorts). I attached the input character below for you to compare against. The model also has a replacement mode that swaps the character into the driving video's scene, but here I used animation mode, which keeps the reference image's scene instead.

rob - comfyui

28,700 Aufrufe • vor 25 Tagen

🎤ElevenLabs v3 is now available on fal! The most expressive Text-to-Speech model with dialogue mode, multi-speaker support, and enhanced voice control across 70+ languages. Create audio that feels real, natural & expressive!
0:10

🎤ElevenLabs v3 is now available on fal! The most expressive Text-to-Speech model with dialogue mode, multi-speaker support, and enhanced voice control across 70+ languages. Create audio that feels real, natural & expressive!

fal

44,525 Aufrufe • vor 11 Monaten