Анализ данных (Data analysis) | Telegram Webview: data_analysis_ml/3639 -

Telegram Group & Telegram Channel

Анализ данных (Data analysis)

🦖 Tokasaurus — универсальный токенизатор с поддержкой 70+ языков

Tokasaurus — это быстрый и лёгкий инструмент для токенизации текста, созданный на базе библиотеки tokenizers от Hugging Face. Он поддерживает более 70 языков программирования и естественных языков.

🔍 Что умеет Tokasaurus:

• ✂️ Разбивает текст на токены для языковых моделей
• 🧠 Поддерживает GPT-совместимые токенизаторы (tiktoken, BPE и другие)
• 🌍 Работает с Python, JavaScript, C++, Rust, Markdown, JSON, YAML и многими другими
• ⚡ Очень быстрый — написан на Rust с Python-обёрткой
• 📦 Используется как CLI, Python-библиотека или Web API

pip install tokasaurus

🧪 Пример использования (Python):


from tokasaurus import tokenize

tokens = tokenize("def hello(): print('Hi')", model="gpt2")
print(tokens)

🎯 Кому подойдёт:

• Тем, кто работает с LLM
• Для оценки длины prompt'ов
• Для предобработки кода и текста
• Для интеграции в пайплайны, IDE, аналитические инструменты

🔗 GitHub: github.com/ScalingIntelligence/tokasaurus

💡 Если тебе нужен универсальный и быстрый токенизатор — попробуй Tokasaurus.

@data_analysis_ml

www.group-telegram.com/it/data_analysis_ml.com/3639

4.4K viewsJun 8 at 09:08

group-telegram.com/data_analysis_ml/3639

Create: 2025-06-08
Last Update: 2025-06-18 14:58:59

🦖 Tokasaurus — универсальный токенизатор с поддержкой 70+ языков

Tokasaurus — это быстрый и лёгкий инструмент для токенизации текста, созданный на базе библиотеки tokenizers от Hugging Face. Он поддерживает более 70 языков программирования и естественных языков.

🔍 Что умеет Tokasaurus:

• ✂️ Разбивает текст на токены для языковых моделей
• 🧠 Поддерживает GPT-совместимые токенизаторы (tiktoken, BPE и другие)
• 🌍 Работает с Python, JavaScript, C++, Rust, Markdown, JSON, YAML и многими другими
• ⚡ Очень быстрый — написан на Rust с Python-обёрткой
• 📦 Используется как CLI, Python-библиотека или Web API

pip install tokasaurus
🧪 Пример использования (Python):


from tokasaurus import tokenize

tokens = tokenize("def hello(): print('Hi')", model="gpt2")
print(tokens)

🎯 Кому подойдёт:

• Тем, кто работает с LLM
• Для оценки длины prompt'ов
• Для предобработки кода и текста
• Для интеграции в пайплайны, IDE, аналитические инструменты

🔗 GitHub: github.com/ScalingIntelligence/tokasaurus

💡 Если тебе нужен универсальный и быстрый токенизатор — попробуй Tokasaurus.

@data_analysis_ml

BY Анализ данных (Data analysis)

Share with your friend now:
group-telegram.com/data_analysis_ml/3639

Open in Telegram

Telegram | DID YOU KNOW?

Date: 2025-06-18|

"There are a lot of things that Telegram could have been doing this whole time. And they know exactly what they are and they've chosen not to do them. That's why I don't trust them," she said. The picture was mixed overseas. Hong Kong’s Hang Seng Index fell 1.6%, under pressure from U.S. regulatory scrutiny on New York-listed Chinese companies. Stocks were more buoyant in Europe, where Frankfurt’s DAX surged 1.4%. The news also helped traders look past another report showing decades-high inflation and shake off some of the volatility from recent sessions. The Bureau of Labor Statistics' February Consumer Price Index (CPI) this week showed another surge in prices even before Russia escalated its attacks in Ukraine. The headline CPI — soaring 7.9% over last year — underscored the sticky inflationary pressures reverberating across the U.S. economy, with everything from groceries to rents and airline fares getting more expensive for everyday consumers. But Telegram says people want to keep their chat history when they get a new phone, and they like having a data backup that will sync their chats across multiple devices. And that is why they let people choose whether they want their messages to be encrypted or not. When not turned on, though, chats are stored on Telegram's services, which are scattered throughout the world. But it has "disclosed 0 bytes of user data to third parties, including governments," Telegram states on its website. Telegram has become more interventionist over time, and has steadily increased its efforts to shut down these accounts. But this has also meant that the company has also engaged with lawmakers more generally, although it maintains that it doesn’t do so willingly. For instance, in September 2021, Telegram reportedly blocked a chat bot in support of (Putin critic) Alexei Navalny during Russia’s most recent parliamentary elections. Pavel Durov was quoted at the time saying that the company was obliged to follow a “legitimate” law of the land. He added that as Apple and Google both follow the law, to violate it would give both platforms a reason to boot the messenger from its stores.
from it

Telegram Анализ данных (Data analysis)
FROM American