Machinelearning | Telegram Webview: ai_machinelearning_big_data/7320 -

Telegram Group & Telegram Channel

Machinelearning

✔️ Учёные Яндекса, НИУ ВШЭ,MIT, ISTA и KAUST разработали новый метод сжатия LLM без использования данных

Недавно был представлен HIGGS (Hadamard Incoherence with Gaussian MSE-optimal GridS) — data-free метод квантизации, который позволяет запускать большие языковые модели локально, за минуты, без GPU.

🔥 Особенности:
🟢Работает без обучающих данных (data-free)
🟢Квантизует даже модели масштаба DeepSeek R1 (671B) и Llama 4 Maverick (400B)
🟢Полностью open-source

📈 Результаты:
🟠Лучшее соотношение качество / размер среди всех data-free методов (NF4, HQQ и др.)
🟠Проверено на Llama 3, Qwen2.5
🟠Статья принята на NAACL 2025

Применение:
▶️Прототипирование без серверов и долгих калибровок
▶️Демократизация доступа к LLM
▶️Подходит для стартапов, исследователей, независимых лабораторий, образовательных и ограниченных сред

🛠 Установка:
pip install flute-kernel

🌟

Пример:

python 
from transformers import AutoModelForCausalLM, AutoTokenizer, HiggsConfig

model = AutoModelForCausalLM.from_pretrained(
    "google/gemma-2-9b-it",
    quantization_config=HiggsConfig(bits=4),
    device_map="auto",
)

🟡

🟡

🟡

GitHub

@ai_machinelearning_big_data

#quantization #LLM #opensource #HIGGS #ai

Please open Telegram to view this post

VIEW IN TELEGRAM

www.group-telegram.com/sg/ai_machinelearning_big_data.com/7319

17.1K viewsApr 11 at 14:32

group-telegram.com/ai_machinelearning_big_data/7320

Create: 2025-04-11
Last Update: 2025-06-14 03:19:58

✔️ Учёные Яндекса, НИУ ВШЭ,MIT, ISTA и KAUST разработали новый метод сжатия LLM без использования данных

Недавно был представлен HIGGS (Hadamard Incoherence with Gaussian MSE-optimal GridS) — data-free метод квантизации, который позволяет запускать большие языковые модели локально, за минуты, без GPU.

🔥 Особенности:
🟢Работает без обучающих данных (data-free)
🟢Квантизует даже модели масштаба DeepSeek R1 (671B) и Llama 4 Maverick (400B)
🟢Полностью open-source

📈 Результаты:
🟠Лучшее соотношение качество / размер среди всех data-free методов (NF4, HQQ и др.)
🟠Проверено на Llama 3, Qwen2.5
🟠Статья принята на NAACL 2025

Применение:
▶️Прототипирование без серверов и долгих калибровок
▶️Демократизация доступа к LLM
▶️Подходит для стартапов, исследователей, независимых лабораторий, образовательных и ограниченных сред

🛠 Установка:
pip install flute-kernel

🌟 Пример:

python 
from transformers import AutoModelForCausalLM, AutoTokenizer, HiggsConfig

model = AutoModelForCausalLM.from_pretrained(
    "google/gemma-2-9b-it",
    quantization_config=HiggsConfig(bits=4),
    device_map="auto",
)

🟡

🟡

🟡

GitHub

@ai_machinelearning_big_data

#quantization #LLM #opensource #HIGGS #ai

BY Machinelearning

Share with your friend now:
group-telegram.com/ai_machinelearning_big_data/7320

Open in Telegram

Telegram | DID YOU KNOW?

Date: 2025-06-14|

Stocks dropped on Friday afternoon, as gains made earlier in the day on hopes for diplomatic progress between Russia and Ukraine turned to losses. Technology stocks were hit particularly hard by higher bond yields. 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. "There are several million Russians who can lift their head up from propaganda and try to look for other sources, and I'd say that most look for it on Telegram," he said. Markets continued to grapple with the economic and corporate earnings implications relating to the Russia-Ukraine conflict. “We have a ton of uncertainty right now,” said Stephanie Link, chief investment strategist and portfolio manager at Hightower Advisors. “We’re dealing with a war, we’re dealing with inflation. We don’t know what it means to earnings.” At this point, however, Durov had already been working on Telegram with his brother, and further planned a mobile-first social network with an explicit focus on anti-censorship. Later in April, he told TechCrunch that he had left Russia and had “no plans to go back,” saying that the nation was currently “incompatible with internet business at the moment.” He added later that he was looking for a country that matched his libertarian ideals to base his next startup.
from sg

Telegram Machinelearning
FROM American