Warning: file_put_contents(aCache/aDaily/post/ai_machinelearning_big_data/-7318-7319-7320-7321-7318-): Failed to open stream: No space left on device in /var/www/group-telegram/post.php on line 50
Machinelearning | Telegram Webview: ai_machinelearning_big_data/7320 -
Telegram Group & Telegram Channel
Telegram Group » United States » Machinelearning » Telegram Webview » Post 7320
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",
)


🟡Paper
🟡Hugging Face
🟡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/7320
17.0K views



group-telegram.com/ai_machinelearning_big_data/7320
Create:
Last Update:

✔️ 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",
)


🟡Paper
🟡Hugging Face
🟡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

View MORE
Open in Telegram


Telegram | DID YOU KNOW?

Date: |

Given the pro-privacy stance of the platform, it’s taken as a given that it’ll be used for a number of reasons, not all of them good. And Telegram has been attached to a fair few scandals related to terrorism, sexual exploitation and crime. Back in 2015, Vox described Telegram as “ISIS’ app of choice,” saying that the platform’s real use is the ability to use channels to distribute material to large groups at once. Telegram has acted to remove public channels affiliated with terrorism, but Pavel Durov reiterated that he had no business snooping on private conversations. This ability to mix the public and the private, as well as the ability to use bots to engage with users has proved to be problematic. In early 2021, a database selling phone numbers pulled from Facebook was selling numbers for $20 per lookup. Similarly, security researchers found a network of deepfake bots on the platform that were generating images of people submitted by users to create non-consensual imagery, some of which involved children. 'Wild West' 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 gold standard of encryption, known as end-to-end encryption, where only the sender and person who receives the message are able to see it, is available on Telegram only when the Secret Chat function is enabled. Voice and video calls are also completely encrypted.
from us



Warning: filemtime(): stat failed for aCache/aDaily/post/ai_machinelearning_big_data/-7318-7319-7320-7321-7318- in /var/www/group-telegram/post.php on line 310

Warning: filemtime(): stat failed for aCache/aDaily/post/ai_machinelearning_big_data/-7318-7319-7320-7321-7318- in /var/www/group-telegram/post.php on line 311

✔️ Учёные Яндекса

 Machinelearning TG
Webview: 7320
Machinelearning.Telegram Webview
Machinelearning Telegram TG Channel
Telegram Updated:
Telegram Machinelearning
FROM American