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/1863
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/1863

View MORE
Open in Telegram


Telegram | DID YOU KNOW?

Date: |

He said that since his platform does not have the capacity to check all channels, it may restrict some in Russia and Ukraine "for the duration of the conflict," but then reversed course hours later after many users complained that Telegram was an important source of information. The SC urges the public to refer to the SC’s I nvestor Alert List before investing. The list contains details of unauthorised websites, investment products, companies and individuals. Members of the public who suspect that they have been approached by unauthorised firms or individuals offering schemes that promise unrealistic returns Although some channels have been removed, the curation process is considered opaque and insufficient by analysts. The War on Fakes channel has repeatedly attempted to push conspiracies that footage from Ukraine is somehow being falsified. One post on the channel from February 24 claimed without evidence that a widely viewed photo of a Ukrainian woman injured in an airstrike in the city of Chuhuiv was doctored and that the woman was seen in a different photo days later without injuries. The post, which has over 600,000 views, also baselessly claimed that the woman's blood was actually makeup or grape juice. READ MORE
from us


Telegram Machine learning Interview
FROM American