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/us/ai_machinelearning_big_data.com/7319

17.2K viewsApr 11 at 14:32

group-telegram.com/ai_machinelearning_big_data/7320

Create: 2025-04-11
Last Update: 2025-06-19 22:09:41

✔️ 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: 2025-06-19|

Channels are not fully encrypted, end-to-end. All communications on a Telegram channel can be seen by anyone on the channel and are also visible to Telegram. Telegram may be asked by a government to hand over the communications from a channel. Telegram has a history of standing up to Russian government requests for data, but how comfortable you are relying on that history to predict future behavior is up to you. Because Telegram has this data, it may also be stolen by hackers or leaked by an internal employee. Telegram was co-founded by Pavel and Nikolai Durov, the brothers who had previously created VKontakte. VK is Russia’s equivalent of Facebook, a social network used for public and private messaging, audio and video sharing as well as online gaming. In January, SimpleWeb reported that VK was Russia’s fourth most-visited website, after Yandex, YouTube and Google’s Russian-language homepage. In 2016, Forbes’ Michael Solomon described Pavel Durov (pictured, below) as the “Mark Zuckerberg of Russia.” "The inflation fire was already hot and now with war-driven inflation added to the mix, it will grow even hotter, setting off a scramble by the world’s central banks to pull back their stimulus earlier than expected," Chris Rupkey, chief economist at FWDBONDS, wrote in an email. "A spike in inflation rates has preceded economic recessions historically and this time prices have soared to levels that once again pose a threat to growth." Andrey, a Russian entrepreneur living in Brazil who, fearing retaliation, asked that NPR not use his last name, said Telegram has become one of the few places Russians can access independent news about the war. 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.
from us

Telegram Machinelearning
FROM American