Machine Learning with Python
67.9K subscribers
1.4K photos
116 videos
188 files
1.09K links
Learn Machine Learning with hands-on Python tutorials, real-world code examples, and clear explanations for researchers and developers.

Admin: @HusseinSheikho || @Hussein_Sheikho
Download Telegram
πŸš€ Sber has released two open-source MoE models: GigaChat-3.1 Ultra and Lightning

Both code and weights are available under the MIT license on HuggingFace.

πŸ‘‰ Key details:

β€’ Trained from scratch (not a finetune) on proprietary data and infrastructure
β€’ Mixture-of-Experts (MoE) architecture

Models:

🧠 GigaChat-3.1 Ultra
β€’ 702B MoE model for high-performance environments
β€’ Outperforms DeepSeek-V3-0324 and Qwen3-235B on math and reasoning benchmarks
β€’ Supports FP8 training and MTP

⚑️ GigaChat-3.1 Lightning
β€’ 10B model (1.8B active parameters)
β€’ Outperforms Qwen3-4B and Gemma-3-4B on Sber benchmarks
β€’ Efficient local inference
β€’ Up to 256k context

Engineering highlights:

β€’ Custom metric to detect and reduce generation loops
β€’ DPO training moved to native FP8
β€’ Improvements in post-training pipeline
β€’ Identified and fixed a critical issue affecting evaluation quality

🌍 Trained on 14 languages (optimized for English and Russian)

Use cases:

β€’ chatbots
β€’ AI assistants
β€’ copilots
β€’ internal ML systems

Sber provides a solid open foundation for developers to build production-ready AI systems with lower infrastructure costs.
❀5πŸ‘3πŸ’―1
πŸš€ $0.15/GB - PROXYFOG.COM β€” SCALE WITHOUT LIMITS

πŸ’Ž Premium Residential & Mobile Proxies
🌍 60M+ Real IPs β€” 195 Countries (πŸ‡ΊπŸ‡Έ USA Included)
πŸ’° Prices as low as $0.15/GB
🎯 Instant & Precise Country Targeting
πŸ”„ Sticky Sessions + Fresh IP on Every Request
♾️ Balance Never Expires

⚑ Built for Arbitrage. Automation. Scraping. Scaling.
⚑ Fast. Stable. High-Performance Infrastructure.

πŸ‘‰ Website:
https://tglink.io/99ba3379f9de68
πŸ“© Telegram:
https://t.iss.one/proxyfog?utm_source=telegain&utm_medium=cpp&utm_campaign=s1&utm_content=codeprogrammer&utm_term=

Start today. Scale without limits. πŸš€
❀5
βœ”οΈ 10 Books to Understand How Large Language Models Function (2026)

1. Deep Learning
https://deeplearningbook.org
The definitive reference for neural networks, covering backpropagation, architectures, and foundational concepts.

2. Artificial Intelligence: A Modern Approach
https://aima.cs.berkeley.edu
A fundamental perspective on artificial intelligence as a comprehensive system.

3. Speech and Language Processing
https://web.stanford.edu/~jurafsky/slp3/
An in-depth examination of natural language processing, transformers, and linguistics.

4. Machine Learning: A Probabilistic Perspective
https://probml.github.io/pml-book/
An exploration of probabilities, statistics, and the theoretical foundations of machine learning.

5. Understanding Deep Learning
https://udlbook.github.io/udlbook/
A contemporary explanation of deep learning principles with strong intuitive insights.

6. Designing Machine Learning Systems
https://oreilly.com/library/view/designing-machine-learning/9781098107956/
Strategies for deploying models into production environments.

7. Generative Deep Learning
https://github.com/3p5ilon/ML-books/blob/main/generative-deep-learning-teaching-machines-to-paint-write-compose-and-play.pdf
Practical applications of generative models and transformer architectures.

8. Natural Language Processing with Transformers
https://dokumen.pub/natural-language-processing-with-transformers-revised-edition-1098136799-9781098136796-9781098103248.html
Methodologies for constructing natural language processing systems based on transformers.

9. Machine Learning Engineering
https://mlebook.com
Principles of machine learning engineering and operational deployment.

10. The Hundred-Page Machine Learning Book
https://themlbook.com
A highly concentrated foundational overview without extraneous detail. πŸ“šπŸ€–
❀6πŸ‘2
Listen, stats don’t lie – analysis of 5,000+ betting accounts shows users who follow smart prediction tips boost their win rate by 32%. BetLife isn’t about fixed matches or empty hype; we give you data-backed insights to help you pick smarter bets. Ready to up your game? Check this out πŸ‘‰ BetLife Channel. Remember, no guarantees, just real tips. Gamble responsibly, folks πŸ”ž #BetSmart #DataDriven
Admin: @betlife_admin

#ad πŸ“’ InsideAd
Please open Telegram to view this post
VIEW IN TELEGRAM
Hyper-Extract πŸš€

It uses LLM to convert unstructured text into structured data. You can input a large amount of "dirty" text, and it will automatically extract the structure and generate a knowledge graph using LLM. πŸ§ πŸ“Š

It includes a CLI utility that can be launched with a single command, as well as more than 80 ready-made domain templates (finance, healthcare, law, etc.) - there's no need to write your own prompts. βš™οΈπŸ“

https://github.com/yifanfeng97/Hyper-Extract πŸ”—
Please open Telegram to view this post
VIEW IN TELEGRAM
❀3
Ever wondered why most bets fail despite β€œsure” tips? It’s not bad luck-it’s missing this ONE simple strategy that pros swear by… Discover how to bet smart, stay safe, and watch stress melt away. Don’t miss out ➑️ Join ο£Ώ πŸ…¨πŸ…žπŸ…€πŸ…πŸ…–πŸ…© πŸ…‘πŸ…”πŸ…£ ο£Ώ

#ad πŸ“’ InsideAd
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘1πŸŽ‰1
The matrix cookbook.pdf
676.5 KB
πŸ“š Notes and Important Formulas ⬅️ "Matrices, Linear Algebra, and Probability"

πŸ‘¨πŸ»β€πŸ’» This booklet serves as an essential resource for individuals initiating their studies in data science. It consolidates comprehensive information on matrices, linear algebra, and probability, thereby eliminating the necessity of consulting multiple sources.

✏️ The document encompasses nearly all pertinent formulas and key concepts. It addresses foundational topics such as determinants and matrix inverses, as well as advanced subjects including eigenvalues, eigenvectors, Singular Value Decomposition (SVD), and probability distributions.

🌐 #DataScience #Python #Math

https://t.iss.one/CodeProgrammer 🌟
Please open Telegram to view this post
VIEW IN TELEGRAM
❀7πŸ‘2
πŸ“ 12 Essential Articles for Data Scientists

🏷 Article: Seq2Seq Learning with NN
https://arxiv.org/pdf/1409.3215
An introduction to Seq2Seq models, which serve as the foundation for machine translation utilizing deep learning.

🏷 Article: GANs
https://arxiv.org/pdf/1406.2661
An introduction to Generative Adversarial Networks (GANs) and the concept of generating synthetic data. This forms the basis for creating images and videos with artificial intelligence.

🏷 Article: Attention is All You Need
https://arxiv.org/pdf/1706.03762
This paper was revolutionary in natural language processing. It introduced the Transformer architecture, which underlies GPT, BERT, and contemporary intelligent language models.

🏷 Article: Deep Residual Learning
https://arxiv.org/pdf/1512.03385
This work introduced the ResNet model, enabling neural networks to achieve greater depth and accuracy without compromising the learning process.

🏷 Article: Batch Normalization
https://arxiv.org/pdf/1502.03167
This paper introduced a technique that facilitates faster and more stable training of neural networks.

🏷 Article: Dropout
https://jmlr.org/papers/volume15/srivastava14a/srivastava14a.pdf
A straightforward method designed to prevent overfitting in neural networks.

🏷 Article: ImageNet Classification with DCNN
https://proceedings.neurips.cc/paper_files/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf
The first successful application of a deep neural network for image recognition.

🏷 Article: Support-Vector Machines
https://link.springer.com/content/pdf/10.1007/BF00994018.pdf
This seminal work introduced the Support Vector Machine (SVM) algorithm, a widely utilized method for data classification.

🏷 Article: A Few Useful Things to Know About ML
https://homes.cs.washington.edu/~pedro/papers/cacm12.pdf
A comprehensive collection of practical and empirical insights regarding machine learning.

🏷 Article: Gradient Boosting Machine
https://www.cse.iitb.ac.in/~soumen/readings/papers/Friedman1999GreedyFuncApprox.pdf
This paper introduced the "Gradient Boosting" method, which serves as the foundation for many modern machine learning models, including XGBoost and LightGBM.

🏷 Article: Latent Dirichlet Allocation
https://jmlr.org/papers/volume3/blei03a/blei03a.pdf
This work introduced a model for text analysis capable of identifying the topics discussed within an article.

🏷 Article: Random Forests
https://www.stat.berkeley.edu/~breiman/randomforest2001.pdf
This paper introduced the "Random Forest" algorithm, a powerful machine learning method that aggregates multiple models to achieve enhanced accuracy.

https://t.iss.one/CodeProgrammer 🌟
Please open Telegram to view this post
VIEW IN TELEGRAM
❀6πŸ‘2
Forwarded from Udemy Free Coupons
HTML, CSS, Java, & JavaScript: Full Stack Programming Course

Master Full Stack Development with HTML, CSS, Java, and JavaScript: Build Dynamic and Responsive Web Applications...

🏷 Category: N/A
🌍 Language: English (US)
πŸ‘₯ Students: 30,877 students
⭐️ Rating: 4.4/5.0 (549 reviews)
πŸƒβ€β™‚οΈ Enrollments Left: N/A
⏳ Expires In: 0D:1H:1M
πŸ’° Price: $23.51 => FREE
πŸ†” Coupon: CM260406IN

⚠️ Note: You may need to watch a short ad to access the course. This helps keep the service free for everyone. πŸ™

πŸ’Ž By: https://t.iss.one/Udemy26
❀2