Telegram Group & Telegram Channel
Forwarded from Machinelearning
🌟MiniMax-M1: открытя reasoning‑LLM с контекстом 1M

MiniMax-M1 — первая в мире open-weight гибридная reasoning‑LLM c 1M контекстом (8× DeepSeek R1) и гибридной архитектурой MoE + lightning attention.
• 456 млрд параметров (45,9 млрд активируются на токен), сверхэффективная генерация — 25% FLOPs DeepSeek R1 на 100K токенов
• Обучение через RL с новым алгоритмом CISPO, решающим реальные задачи от математики до кодинга
• На обучение было потрачено $534K, две версии — 40K/80K “thinking budget”
• Обходит DeepSeek R1 и Qwen3-235B на бенчмарках по математике и кодингу,
• Топ результат на задачах для software engineering и reasoning



Бенчмарки:
AIME 2024: 86.0 (M1-80K) vs 85.7 (Qwen3) vs 79.8 (DeepSeek R1)

SWE-bench Verified: 56.0 vs 34.4 (Qwen3)

OpenAI-MRCR (128k): 73.4 vs 27.7 (Qwen3)

TAU-bench (airline): 62.0 vs 34.7 (Qwen3)

LongBench-v2: 61.5 vs 50.1 (Qwen3)


➡️ Попробовать можно здесь

Hugging Face: https://huggingface.co/collections/MiniMaxAI/minimax-m1-68502ad9634ec0eeac8cf094
GitHub: https://github.com/MiniMax-AI/MiniMax-M1
Tech Report: https://github.com/MiniMax-AI/MiniMax-M1/blob/main/MiniMax_M1_tech_report.pdf


@ai_machinelearning_big_data

#llm #reasoningmodels #minimaxm1
Please open Telegram to view this post
VIEW IN TELEGRAM



group-telegram.com/machinelearning_interview/1862
Create:
Last Update:

🌟MiniMax-M1: открытя reasoning‑LLM с контекстом 1M

MiniMax-M1 — первая в мире open-weight гибридная reasoning‑LLM c 1M контекстом (8× DeepSeek R1) и гибридной архитектурой MoE + lightning attention.
• 456 млрд параметров (45,9 млрд активируются на токен), сверхэффективная генерация — 25% FLOPs DeepSeek R1 на 100K токенов
• Обучение через RL с новым алгоритмом CISPO, решающим реальные задачи от математики до кодинга
• На обучение было потрачено $534K, две версии — 40K/80K “thinking budget”
• Обходит DeepSeek R1 и Qwen3-235B на бенчмарках по математике и кодингу,
• Топ результат на задачах для software engineering и reasoning



Бенчмарки:
AIME 2024: 86.0 (M1-80K) vs 85.7 (Qwen3) vs 79.8 (DeepSeek R1)

SWE-bench Verified: 56.0 vs 34.4 (Qwen3)

OpenAI-MRCR (128k): 73.4 vs 27.7 (Qwen3)

TAU-bench (airline): 62.0 vs 34.7 (Qwen3)

LongBench-v2: 61.5 vs 50.1 (Qwen3)


➡️ Попробовать можно здесь

Hugging Face: https://huggingface.co/collections/MiniMaxAI/minimax-m1-68502ad9634ec0eeac8cf094
GitHub: https://github.com/MiniMax-AI/MiniMax-M1
Tech Report: https://github.com/MiniMax-AI/MiniMax-M1/blob/main/MiniMax_M1_tech_report.pdf


@ai_machinelearning_big_data

#llm #reasoningmodels #minimaxm1

BY Machine learning Interview





Share with your friend now:
group-telegram.com/machinelearning_interview/1862

View MORE
Open in Telegram


Telegram | DID YOU KNOW?

Date: |

"Your messages about the movement of the enemy through the official chatbot … bring new trophies every day," the government agency tweeted. For Oleksandra Tsekhanovska, head of the Hybrid Warfare Analytical Group at the Kyiv-based Ukraine Crisis Media Center, the effects are both near- and far-reaching. On Telegram’s website, it says that Pavel Durov “supports Telegram financially and ideologically while Nikolai (Duvov)’s input is technological.” Currently, the Telegram team is based in Dubai, having moved around from Berlin, London and Singapore after departing Russia. Meanwhile, the company which owns Telegram is registered in the British Virgin Islands. Since January 2022, the SC has received a total of 47 complaints and enquiries on illegal investment schemes promoted through Telegram. These fraudulent schemes offer non-existent investment opportunities, promising very attractive and risk-free returns within a short span of time. They commonly offer unrealistic returns of as high as 1,000% within 24 hours or even within a few hours. The regulator said it has been undertaking several campaigns to educate the investors to be vigilant while taking investment decisions based on stock tips.
from ar


Telegram Machine learning Interview
FROM American