Загрузка видео...

Не удалось загрузить видео

На главную

We're excited to introduce Arcee.ai's Trinity Large model. An open 400B parameter Mixture of Experts model, delivering frontier-level performance with only 13B active parameters. Trained in collaboration between Arcee, Datology and Prime Intellect.

PrimeIntellect's profile picture

Prime Intellect

66,030 subscribers

178,830 просмотров • 5 месяцев назад •via X (Twitter)

Новости и политикаНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

We're excited to introduce Ocelot, an open-source and Brave-trained AI model built specifically to summarize web content. Ocelot is now available in Leo, our browser's AI assistant, and as an open-source model for the developer community.
0:12

We're excited to introduce Ocelot, an open-source and Brave-trained AI model built specifically to summarize web content. Ocelot is now available in Leo, our browser's AI assistant, and as an open-source model for the developer community.

Brave

100,685 просмотров • 2 месяцев назад

We are excited to introduce Mercury, the first commercial-grade diffusion large language model (dLLM)! dLLMs push the frontier of intelligence and speed with parallel, coarse-to-fine text generation.
0:19

We are excited to introduce Mercury, the first commercial-grade diffusion large language model (dLLM)! dLLMs push the frontier of intelligence and speed with parallel, coarse-to-fine text generation.

Inception

1,912,676 просмотров • 1 год назад

1/3 🚀Thrilled to introduce Wan2.1-FLF2V-14B - our first 14B-parameter large model for First-Last-Frame to video generation! Open-source, open-source, open-source! Empowering digital artists with unprecedented efficiency and creative flexibility. #wan #AIGC #alart
0:18

1/3 🚀Thrilled to introduce Wan2.1-FLF2V-14B - our first 14B-parameter large model for First-Last-Frame to video generation! Open-source, open-source, open-source! Empowering digital artists with unprecedented efficiency and creative flexibility. #wan #AIGC #alart

Wan

196,659 просмотров • 1 год назад

Trinity-Large-Thinking, Arcee.ai's latest model, is now free on Nous Portal for the next week Sign up for Nous Portal to use it in your Hermes Agent today
0:12

Trinity-Large-Thinking, Arcee.ai's latest model, is now free on Nous Portal for the next week Sign up for Nous Portal to use it in your Hermes Agent today

Nous Research

225,774 просмотров • 2 месяцев назад

Poolside is hosting a 2-day model research hackathon in London. Join us to push an open-weight agent model as far as you can. RL and fine-tune Laguna XS.2, our latest-generation model, on Prime Intellect Lab. Dates: May 29–30 Partners: NVIDIA + Prime Intellect + Hugging Face Prize: NVIDIA DGX Spark Agents need better models. Better models need cracked researchers. Link below.
0:15

Poolside is hosting a 2-day model research hackathon in London. Join us to push an open-weight agent model as far as you can. RL and fine-tune Laguna XS.2, our latest-generation model, on Prime Intellect Lab. Dates: May 29–30 Partners: NVIDIA + Prime Intellect + Hugging Face Prize: NVIDIA DGX Spark Agents need better models. Better models need cracked researchers. Link below.

Poolside

92,613 просмотров • 1 месяц назад

Sparsely activated models like MOEs and Apple silicon + MLX are a great match. - Lots of RAM to hold the entire model in memory (not just the active parameters). For an MOE at each token you access basically a random subset of the model. Swapping large parts of the model to "disk" from token-to-token is too slow. - Comparatively you don't need as much memory bandwidth. Only a small fraction of the weights are used per token. In the case of DeepSeek v3 37B / 671B are active. So only ~5% of the weights are moved to GPU cache / register for each token. (SVG animation made with the help of DeepSeek V2 1210 + MLX on an M2 Ultra)
0:11

Sparsely activated models like MOEs and Apple silicon + MLX are a great match. - Lots of RAM to hold the entire model in memory (not just the active parameters). For an MOE at each token you access basically a random subset of the model. Swapping large parts of the model to "disk" from token-to-token is too slow. - Comparatively you don't need as much memory bandwidth. Only a small fraction of the weights are used per token. In the case of DeepSeek v3 37B / 671B are active. So only ~5% of the weights are moved to GPU cache / register for each token. (SVG animation made with the help of DeepSeek V2 1210 + MLX on an M2 Ultra)

Awni Hannun

27,452 просмотров • 1 год назад

Semantic search improves our agent's accuracy across all frontier models, especially in large codebases where grep alone falls short. Learn more about our results and how we trained an embedding model for retrieving code.
0:12

Semantic search improves our agent's accuracy across all frontier models, especially in large codebases where grep alone falls short. Learn more about our results and how we trained an embedding model for retrieving code.

Cursor

881,522 просмотров • 8 месяцев назад

Today IBM announced it will host @MetaAI's Llama 2-chat 70 billion parameter model in the watsonx․ai studio, furthering their collaboration on open innovation for #AI. Learn more:
0:10

Today IBM announced it will host @MetaAI's Llama 2-chat 70 billion parameter model in the watsonx․ai studio, furthering their collaboration on open innovation for #AI. Learn more:

IBM News

930,986 просмотров • 2 лет назад

Another demo of the iPhone 17 Pro’s on-device LLM performance This time with Ling mini 2.0 by InclusionAI, a 16B MoE model with 1.4B active parameters running at ~120tk/s Thanks to Awni Hannun for the MLX DWQ 2-bit quants
0:11

Another demo of the iPhone 17 Pro’s on-device LLM performance This time with Ling mini 2.0 by InclusionAI, a 16B MoE model with 1.4B active parameters running at ~120tk/s Thanks to Awni Hannun for the MLX DWQ 2-bit quants

Adrien Grondin

46,205 просмотров • 9 месяцев назад

Snap presents MoA Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation We introduce a new architecture for personalization of text-to-image diffusion models, coined Mixture-of-Attention (MoA). Inspired by the Mixture-of-Experts
0:11

Snap presents MoA Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation We introduce a new architecture for personalization of text-to-image diffusion models, coined Mixture-of-Attention (MoA). Inspired by the Mixture-of-Experts

AK

47,488 просмотров • 2 лет назад

The fact that a 284B parameter model is able to in a single 400K token session - ssh into my Homelab to find docs - ssh into lambda / prime intellect - rewrite reap to support the DS4 attention - download models & datasets - run tests to check it works
0:13

The fact that a 284B parameter model is able to in a single 400K token session - ssh into my Homelab to find docs - ssh into lambda / prime intellect - rewrite reap to support the DS4 attention - download models & datasets - run tests to check it works

0xSero

22,762 просмотров • 1 месяц назад

We're very excited to introduce TAPNext: a model that sets a new state-of-art for Tracking Any Point in videos, by formulating the task as Next Token Prediction. For more, see: 🧵
0:12

We're very excited to introduce TAPNext: a model that sets a new state-of-art for Tracking Any Point in videos, by formulating the task as Next Token Prediction. For more, see: 🧵

Carl Doersch

45,247 просмотров • 1 год назад

it's crazy what a 1.5B model can do these days! "VibeThinker-1.5B is a 1.5-billion parameter dense language model. With a total training cost of only $7,800 USD, it achieves reasoning performance comparable to larger models like GPT OSS-20B Medium." runs perfectly on device!
0:18

it's crazy what a 1.5B model can do these days! "VibeThinker-1.5B is a 1.5-billion parameter dense language model. With a total training cost of only $7,800 USD, it achieves reasoning performance comparable to larger models like GPT OSS-20B Medium." runs perfectly on device!

Maziyar PANAHI

202,328 просмотров • 7 месяцев назад

starting the week with a true groundbreaking work 💥 Large Language Diffusion Models the first billion-parameter scale diffusion model competitive with its pairs (8B model comparable to LLaMA 3 8B) it gets rid of the michael scott syndrome on existing LLMs
0:12

starting the week with a true groundbreaking work 💥 Large Language Diffusion Models the first billion-parameter scale diffusion model competitive with its pairs (8B model comparable to LLaMA 3 8B) it gets rid of the michael scott syndrome on existing LLMs

apolinario 🌐

11,833 просмотров • 1 год назад

🚨 We're very happy to introduce TRIBE v2: a foundation model of the brain's responses to sight, sound & language. 📄 Paper: ▶️ Demo: 💻 Code: 🤗 Model:
0:16

🚨 We're very happy to introduce TRIBE v2: a foundation model of the brain's responses to sight, sound & language. 📄 Paper: ▶️ Demo: 💻 Code: 🤗 Model:

Stéphane d'Ascoli

121,477 просмотров • 3 месяцев назад

today, we're releasing an open version of Krea-1. FLUX Krea is a new SOTA open-source image model with incredible realism and aesthetics. try it for free 👇
0:19

today, we're releasing an open version of Krea-1. FLUX Krea is a new SOTA open-source image model with incredible realism and aesthetics. try it for free 👇

Krea

1,055,727 просмотров • 11 месяцев назад

🚀Excited to announce: Open-source AlphaFold3 implementation! 🚀 I am thrilled to announce one of the models we have been building for the last 8-weeks at Ligo - an open-source implementation of DeepMind’s frontier model, AlphaFold3! Here’s what we have learned, a thread (1/11):
0:14

🚀Excited to announce: Open-source AlphaFold3 implementation! 🚀 I am thrilled to announce one of the models we have been building for the last 8-weeks at Ligo - an open-source implementation of DeepMind’s frontier model, AlphaFold3! Here’s what we have learned, a thread (1/11):

Arda Göreci

342,063 просмотров • 1 год назад

You don't need a more expensive model. You need better reasoning. Every frontier LLM got smarter with SERV: - smaller ones match frontier performance - frontier ones go past what they were built for The question isn't which model to choose - it's what engine it runs on.
0:11

You don't need a more expensive model. You need better reasoning. Every frontier LLM got smarter with SERV: - smaller ones match frontier performance - frontier ones go past what they were built for The question isn't which model to choose - it's what engine it runs on.

OpenServ

29,525 просмотров • 1 месяц назад

EAGLE-3 introduces two key innovations: Training-Time Testing (TTT) and multi-level feature fusion. By removing the feature prediction constraint used in previous EAGLE versions and leveraging semantic features across multiple layers, EAGLE-3 achieves higher acceptance rates, faster generation, and lossless performance. The result? - 5.6× faster than vanilla decoding (13B) Compared to EAGLE-1, EAGLE-3 delivers a 1.8× speedup on the 13B model, with the future EAGLE-4 release expected to further improve decoding efficiency. *Inference on the video conducted on 2x RTX 3090 GPUs at fp16 precision using the Vicuna 13B model.
0:12

EAGLE-3 introduces two key innovations: Training-Time Testing (TTT) and multi-level feature fusion. By removing the feature prediction constraint used in previous EAGLE versions and leveraging semantic features across multiple layers, EAGLE-3 achieves higher acceptance rates, faster generation, and lossless performance. The result? - 5.6× faster than vanilla decoding (13B) Compared to EAGLE-1, EAGLE-3 delivers a 1.8× speedup on the 13B model, with the future EAGLE-4 release expected to further improve decoding efficiency. *Inference on the video conducted on 2x RTX 3090 GPUs at fp16 precision using the Vicuna 13B model.

Eagle

36,976 просмотров • 23 дней назад

We’re releasing model weights for our 8B- parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. Learn more about how Dynamic Byte Latent Transformer is paving the way for groundbreaking developments in the field of language modeling. Read the research paper, and download the model and code.
0:12

We’re releasing model weights for our 8B- parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. Learn more about how Dynamic Byte Latent Transformer is paving the way for groundbreaking developments in the field of language modeling. Read the research paper, and download the model and code.

AI at Meta

195,546 просмотров • 1 год назад