GigaChat 3.5 Ultra Publicly Released — The New Generation of the Flagship Model
What’s inside:
🔘 A proprietary hybrid MLA + Gated DeltaNet architecture with a dedicated stabilization framework, without which this hybrid setup would not train reliably at this scale;
🔘 Gated Attention: the model can locally down-weight overly strong signals from the attention layer;
🔘 GatedNorm: normalization with an explicit gate that controls signal magnitude across features;
🔘 Approximately 4x lower KV cache per token: with the same memory budget, the model can support 2.14x longer context and deliver a 20% throughput increase under load;
🔘 Two MTP heads, enabling up to 2.2x faster generation;
🔘 FP8 across all training stages with no quality degradation compared with bf16, enabled by custom Triton and CUDA kernels;
🔘 A new online RL stage after SFT and DPO.
Results:
🔘 GigaChat-3.5-Ultra-Base outperforms DeepSeek V3.2 Exp Base and DeepSeek V4 Flash Base on average across a set of general, math, and code benchmarks:
🔘 GigaChat-3.5-Ultra-Instruct is comparable to DeepSeek V3.2 in terms of average score, despite having half the size;
🔘 According to the MiniMax-M2.7 LLM judge, the average win rate against GigaChat 3.1 Ultra is 75.9%, and against GPT-5 is 68.7%.
➡️ HuggingFace
The GigaChat team has released GigaChat 3.5 Ultra as open source—a new 432B model under the MIT license. This is the first open-source hybrid of GatedDeltaNet and MLA scaled to hundreds of billions of parameters, featuring a proprietary training recipe we refined through more than 1,500 experiments. The model has grown in terms of code, mathematics, agent scenarios, and application domains—yet it’s 40% smaller than GigaChat 3.1 Ultra.
What’s inside:
Results:
The entire stack — data (our own LLM-filtered Common Crawl, 600+ programming languages in the code), architecture, training methodology, and infrastructure — was built end-to-end by GigaChat team.
Please open Telegram to view this post
VIEW IN TELEGRAM
❤3
📚 Frequently Asked Pandas Interview Questions (Beginner Level)
1️⃣ What is the difference between a Series and a DataFrame?
💡 Answer:
Series → A one-dimensional labeled array.
DataFrame → A two-dimensional table with rows and columns.
2️⃣ How do you find missing
values in a DataFrame?
💡 Answer:
3️⃣ What is the difference between loc and iloc?
💡 Answer:
4️⃣ What is the difference between merge() and concat()?
💡 Answer:
React ♥️ for more interview questions
1️⃣ What is the difference between a Series and a DataFrame?
💡 Answer:
Series → A one-dimensional labeled array.
DataFrame → A two-dimensional table with rows and columns.
2️⃣ How do you find missing
values in a DataFrame?
💡 Answer:
df.isnull().sum()
This returns the number of missing values in each column.3️⃣ What is the difference between loc and iloc?
💡 Answer:
loc → Label-based indexing.iloc → Integer position-based indexing.4️⃣ What is the difference between merge() and concat()?
💡 Answer:
merge() combines DataFrames using a common key (similar to an SQL JOIN).concat() combines DataFrames by stacking them vertically or horizontally.React ♥️ for more interview questions
❤10
Aaj hi ek certified Hackar bano!💻
Shuru se saari cheeze seekho bilkul basic se!!
PW skills leke aaya h certified Ethical Hacking ka course!!
Isme milega :
✅ Hands on Practice
✅ LIVE Hacking Labs
✅ Certificate after Completion
Sirf Rs 4999 mai
Abhi enroll karo HACK30 Coupon code use karke 30% OFF milega!
Enroll NOW : https://pwskills.com/web-development/certified-ethical-hacking-course-035473/?source=pwskills.com&position=course_dropdown&from=home_page&utm_source=pwskills&utm_medium=telegram&utm_campaign=ethical_hacking
Shuru se saari cheeze seekho bilkul basic se!!
PW skills leke aaya h certified Ethical Hacking ka course!!
Isme milega :
✅ Hands on Practice
✅ LIVE Hacking Labs
✅ Certificate after Completion
Sirf Rs 4999 mai
Abhi enroll karo HACK30 Coupon code use karke 30% OFF milega!
Enroll NOW : https://pwskills.com/web-development/certified-ethical-hacking-course-035473/?source=pwskills.com&position=course_dropdown&from=home_page&utm_source=pwskills&utm_medium=telegram&utm_campaign=ethical_hacking
❤2
🚀 How to Land a Data Analyst Job Without Experience?
Many people asked me this question, so I thought to answer it here to help everyone. Here is the step-by-step approach i would recommend:
✅ Step 1: Master the Essential Skills
You need to build a strong foundation in:
🔹 SQL – Learn how to extract and manipulate data
🔹 Excel – Master formulas, Pivot Tables, and dashboards
🔹 Python – Focus on Pandas, NumPy, and Matplotlib for data analysis
🔹 Power BI/Tableau – Learn to create interactive dashboards
🔹 Statistics & Business Acumen – Understand data trends and insights
Where to learn?
📌 Google Data Analytics Course
📌 SQL – Mode Analytics (Free)
📌 Python – Kaggle or DataCamp
✅ Step 2: Work on Real-World Projects
Employers care more about what you can do rather than just your degree. Build 3-4 projects to showcase your skills.
🔹 Project Ideas:
✅ Analyze sales data to find profitable products
✅ Clean messy datasets using SQL or Python
✅ Build an interactive Power BI dashboard
✅ Predict customer churn using machine learning (optional)
Use Kaggle, Data.gov, or Google Dataset Search to find free datasets!
✅ Step 3: Build an Impressive Portfolio
Once you have projects, showcase them! Create:
📌 A GitHub repository to store your SQL/Python code
📌 A Tableau or Power BI Public Profile for dashboards
📌 A Medium or LinkedIn post explaining your projects
A strong portfolio = More job opportunities! 💡
✅ Step 4: Get Hands-On Experience
If you don’t have experience, create your own!
📌 Do freelance projects on Upwork/Fiverr
📌 Join an internship or volunteer for NGOs
📌 Participate in Kaggle competitions
📌 Contribute to open-source projects
Real-world practice > Theoretical knowledge!
✅ Step 5: Optimize Your Resume & LinkedIn Profile
Your resume should highlight:
✔️ Skills (SQL, Python, Power BI, etc.)
✔️ Projects (Brief descriptions with links)
✔️ Certifications (Google Data Analytics, Coursera, etc.)
Bonus Tip:
🔹 Write "Data Analyst in Training" on LinkedIn
🔹 Start posting insights from your learning journey
🔹 Engage with recruiters & join LinkedIn groups
✅ Step 6: Start Applying for Jobs
Don’t wait for the perfect job—start applying!
📌 Apply on LinkedIn, Indeed, and company websites
📌 Network with professionals in the industry
📌 Be ready for SQL & Excel assessments
Pro Tip: Even if you don’t meet 100% of the job requirements, apply anyway! Many companies are open to hiring self-taught analysts.
You don’t need a fancy degree to become a Data Analyst. Skills + Projects + Networking = Your job offer!
🔥 Your Challenge: Start your first project today and track your progress!
Share with credits: https://t.me/sqlspecialist
Hope it helps :)
Many people asked me this question, so I thought to answer it here to help everyone. Here is the step-by-step approach i would recommend:
✅ Step 1: Master the Essential Skills
You need to build a strong foundation in:
🔹 SQL – Learn how to extract and manipulate data
🔹 Excel – Master formulas, Pivot Tables, and dashboards
🔹 Python – Focus on Pandas, NumPy, and Matplotlib for data analysis
🔹 Power BI/Tableau – Learn to create interactive dashboards
🔹 Statistics & Business Acumen – Understand data trends and insights
Where to learn?
📌 Google Data Analytics Course
📌 SQL – Mode Analytics (Free)
📌 Python – Kaggle or DataCamp
✅ Step 2: Work on Real-World Projects
Employers care more about what you can do rather than just your degree. Build 3-4 projects to showcase your skills.
🔹 Project Ideas:
✅ Analyze sales data to find profitable products
✅ Clean messy datasets using SQL or Python
✅ Build an interactive Power BI dashboard
✅ Predict customer churn using machine learning (optional)
Use Kaggle, Data.gov, or Google Dataset Search to find free datasets!
✅ Step 3: Build an Impressive Portfolio
Once you have projects, showcase them! Create:
📌 A GitHub repository to store your SQL/Python code
📌 A Tableau or Power BI Public Profile for dashboards
📌 A Medium or LinkedIn post explaining your projects
A strong portfolio = More job opportunities! 💡
✅ Step 4: Get Hands-On Experience
If you don’t have experience, create your own!
📌 Do freelance projects on Upwork/Fiverr
📌 Join an internship or volunteer for NGOs
📌 Participate in Kaggle competitions
📌 Contribute to open-source projects
Real-world practice > Theoretical knowledge!
✅ Step 5: Optimize Your Resume & LinkedIn Profile
Your resume should highlight:
✔️ Skills (SQL, Python, Power BI, etc.)
✔️ Projects (Brief descriptions with links)
✔️ Certifications (Google Data Analytics, Coursera, etc.)
Bonus Tip:
🔹 Write "Data Analyst in Training" on LinkedIn
🔹 Start posting insights from your learning journey
🔹 Engage with recruiters & join LinkedIn groups
✅ Step 6: Start Applying for Jobs
Don’t wait for the perfect job—start applying!
📌 Apply on LinkedIn, Indeed, and company websites
📌 Network with professionals in the industry
📌 Be ready for SQL & Excel assessments
Pro Tip: Even if you don’t meet 100% of the job requirements, apply anyway! Many companies are open to hiring self-taught analysts.
You don’t need a fancy degree to become a Data Analyst. Skills + Projects + Networking = Your job offer!
🔥 Your Challenge: Start your first project today and track your progress!
Share with credits: https://t.me/sqlspecialist
Hope it helps :)
❤7
𝐓𝐢𝐩𝐬 𝐟𝐨𝐫 𝐏𝐲𝐭𝐡𝐨𝐧 𝐂𝐨𝐝𝐢𝐧𝐠 𝐢𝐧 𝐃𝐚𝐭𝐚 𝐀𝐧𝐚𝐥𝐲𝐭𝐢𝐜𝐬:
𝘐 𝘨𝘦𝘵 𝘴𝘰 𝘮𝘢𝘯𝘺 𝘲𝘶𝘦𝘴𝘵𝘪𝘰𝘯𝘴 𝘧𝘳𝘰𝘮 𝘥𝘢𝘵𝘢 𝘢𝘯𝘢𝘭𝘺𝘵𝘪𝘤𝘴 𝘢𝘴𝘱𝘪𝘳𝘢𝘯𝘵𝘴 𝘢𝘯𝘥 𝘱𝘳𝘰𝘧𝘦𝘴𝘴𝘪𝘰𝘯𝘢𝘭𝘴 𝘰𝘯 𝘩𝘰𝘸 𝘵𝘰 𝘨𝘢𝘪𝘯 𝘤𝘰𝘮𝘮𝘢𝘯𝘥 𝘰𝘧 𝘗𝘺𝘵𝘩𝘰𝘯.
📍𝐋𝐞𝐚𝐫𝐧 𝐂𝐨𝐫𝐞 𝐏𝐲𝐭𝐡𝐨𝐧 𝐋𝐢𝐛𝐫𝐚𝐫𝐢𝐞𝐬: Master Python libraries for data analytics, like
-pandas for dataframes,
-NumPy for numerical operations,
-Matplotlib/Seaborn for plotting,
-scikit-learn for machine learning.
📍𝐔𝐧𝐝𝐞𝐫𝐬𝐭𝐚𝐧𝐝 𝐂𝐨𝐧𝐜𝐞𝐩𝐭𝐬: Important concepts like list comprehensions, lambda functions, object-oriented programming, and error handling to write efficient code.
📍𝐔𝐬𝐞 𝐏𝐫𝐨𝐛𝐥𝐞𝐦-𝐒𝐨𝐥𝐯𝐢𝐧𝐠 𝐌𝐞𝐭𝐡𝐨𝐝𝐬: Apply data wrangling techniques, efficient loops, and vectorized operations in NumPy/pandas for optimized performance.
📍𝐃𝐨 𝐌𝐨𝐜𝐤 𝐏𝐫𝐨𝐣𝐞𝐜𝐭𝐬: Work on end-to-end Python analytics projects—data loading, cleaning, analysis, and visualization.
📍𝐋𝐞𝐚𝐫𝐧 𝐟𝐫𝐨𝐦 𝐏𝐚𝐬𝐭 𝐏𝐫𝐨𝐣𝐞𝐜𝐭𝐬: Review your previous Python projects to see where your code can be more efficient.
Like this post if you need more resources like this 👍❤️
𝘐 𝘨𝘦𝘵 𝘴𝘰 𝘮𝘢𝘯𝘺 𝘲𝘶𝘦𝘴𝘵𝘪𝘰𝘯𝘴 𝘧𝘳𝘰𝘮 𝘥𝘢𝘵𝘢 𝘢𝘯𝘢𝘭𝘺𝘵𝘪𝘤𝘴 𝘢𝘴𝘱𝘪𝘳𝘢𝘯𝘵𝘴 𝘢𝘯𝘥 𝘱𝘳𝘰𝘧𝘦𝘴𝘴𝘪𝘰𝘯𝘢𝘭𝘴 𝘰𝘯 𝘩𝘰𝘸 𝘵𝘰 𝘨𝘢𝘪𝘯 𝘤𝘰𝘮𝘮𝘢𝘯𝘥 𝘰𝘧 𝘗𝘺𝘵𝘩𝘰𝘯.
📍𝐋𝐞𝐚𝐫𝐧 𝐂𝐨𝐫𝐞 𝐏𝐲𝐭𝐡𝐨𝐧 𝐋𝐢𝐛𝐫𝐚𝐫𝐢𝐞𝐬: Master Python libraries for data analytics, like
-pandas for dataframes,
-NumPy for numerical operations,
-Matplotlib/Seaborn for plotting,
-scikit-learn for machine learning.
📍𝐔𝐧𝐝𝐞𝐫𝐬𝐭𝐚𝐧𝐝 𝐂𝐨𝐧𝐜𝐞𝐩𝐭𝐬: Important concepts like list comprehensions, lambda functions, object-oriented programming, and error handling to write efficient code.
📍𝐔𝐬𝐞 𝐏𝐫𝐨𝐛𝐥𝐞𝐦-𝐒𝐨𝐥𝐯𝐢𝐧𝐠 𝐌𝐞𝐭𝐡𝐨𝐝𝐬: Apply data wrangling techniques, efficient loops, and vectorized operations in NumPy/pandas for optimized performance.
📍𝐃𝐨 𝐌𝐨𝐜𝐤 𝐏𝐫𝐨𝐣𝐞𝐜𝐭𝐬: Work on end-to-end Python analytics projects—data loading, cleaning, analysis, and visualization.
📍𝐋𝐞𝐚𝐫𝐧 𝐟𝐫𝐨𝐦 𝐏𝐚𝐬𝐭 𝐏𝐫𝐨𝐣𝐞𝐜𝐭𝐬: Review your previous Python projects to see where your code can be more efficient.
Like this post if you need more resources like this 👍❤️
❤5
If you’re a student, graduate, or someone looking for a career switch, read this.
Most people spend months watching random YouTube videos and still don’t become job-ready.
Instead, learn in a structured offline classroom.
📌 Data Analytics with GenAI
📌 Python + SQL + Power BI
📌 6-Month Program
📌 1:1 Mentorship
📌 Job Assistance
📍Now available in your city.
Seats are limited.
👉 Register Here: https://lp.pwskills.com/data-analytics-course-offline-batch0?utm_source=telegram&utm_medium=influencer&utm_campaign=daoffline
Most people spend months watching random YouTube videos and still don’t become job-ready.
Instead, learn in a structured offline classroom.
📌 Data Analytics with GenAI
📌 Python + SQL + Power BI
📌 6-Month Program
📌 1:1 Mentorship
📌 Job Assistance
📍Now available in your city.
Seats are limited.
👉 Register Here: https://lp.pwskills.com/data-analytics-course-offline-batch0?utm_source=telegram&utm_medium=influencer&utm_campaign=daoffline
Complete roadmap to learn Python for data analysis
Step 1: Fundamentals of Python
1. Basics of Python Programming
- Introduction to Python
- Data types (integers, floats, strings, booleans)
- Variables and constants
- Basic operators (arithmetic, comparison, logical)
2. Control Structures
- Conditional statements (if, elif, else)
- Loops (for, while)
- List comprehensions
3. Functions and Modules
- Defining functions
- Function arguments and return values
- Importing modules
- Built-in functions vs. user-defined functions
4. Data Structures
- Lists, tuples, sets, dictionaries
- Manipulating data structures (add, remove, update elements)
Step 2: Advanced Python
1. File Handling
- Reading from and writing to files
- Working with different file formats (txt, csv, json)
2. Error Handling
- Try, except blocks
- Handling exceptions and errors gracefully
3. Object-Oriented Programming (OOP)
- Classes and objects
- Inheritance and polymorphism
- Encapsulation
Step 3: Libraries for Data Analysis
1. NumPy
- Understanding arrays and array operations
- Indexing, slicing, and iterating
- Mathematical functions and statistical operations
2. Pandas
- Series and DataFrames
- Reading and writing data (csv, excel, sql, json)
- Data cleaning and preparation
- Merging, joining, and concatenating data
- Grouping and aggregating data
3. Matplotlib and Seaborn
- Data visualization with Matplotlib
- Plotting different types of graphs (line, bar, scatter, histogram)
- Customizing plots
- Advanced visualizations with Seaborn
Step 4: Data Manipulation and Analysis
1. Data Wrangling
- Handling missing values
- Data transformation
- Feature engineering
2. Exploratory Data Analysis (EDA)
- Descriptive statistics
- Data visualization techniques
- Identifying patterns and outliers
3. Statistical Analysis
- Hypothesis testing
- Correlation and regression analysis
- Probability distributions
Step 5: Advanced Topics
1. Time Series Analysis
- Working with datetime objects
- Time series decomposition
- Forecasting models
2. Machine Learning Basics
- Introduction to machine learning
- Supervised vs. unsupervised learning
- Using Scikit-Learn for machine learning
- Building and evaluating models
3. Big Data and Cloud Computing
- Introduction to big data frameworks (e.g., Hadoop, Spark)
- Using cloud services for data analysis (e.g., AWS, Google Cloud)
Step 6: Practical Projects
1. Hands-on Projects
- Analyzing datasets from Kaggle
- Building interactive dashboards with Plotly or Dash
- Developing end-to-end data analysis projects
2. Collaborative Projects
- Participating in data science competitions
- Contributing to open-source projects
👨💻 FREE Resources to Learn & Practice Python
1. https://www.freecodecamp.org/learn/data-analysis-with-python/#data-analysis-with-python-course
2. https://www.hackerrank.com/domains/python
3. https://www.hackerearth.com/practice/python/getting-started/numbers/practice-problems/
4. https://t.me/PythonInterviews
5. https://www.w3schools.com/python/python_exercises.asp
6. https://t.me/pythonfreebootcamp/134
7. https://t.me/pythonanalyst
8. https://pythonbasics.org/exercises/
9. https://t.me/pythondevelopersindia/300
10. https://www.geeksforgeeks.org/python-programming-language/learn-python-tutorial
11. https://t.me/pythonspecialist/33
*React ♥️ for more*
Step 1: Fundamentals of Python
1. Basics of Python Programming
- Introduction to Python
- Data types (integers, floats, strings, booleans)
- Variables and constants
- Basic operators (arithmetic, comparison, logical)
2. Control Structures
- Conditional statements (if, elif, else)
- Loops (for, while)
- List comprehensions
3. Functions and Modules
- Defining functions
- Function arguments and return values
- Importing modules
- Built-in functions vs. user-defined functions
4. Data Structures
- Lists, tuples, sets, dictionaries
- Manipulating data structures (add, remove, update elements)
Step 2: Advanced Python
1. File Handling
- Reading from and writing to files
- Working with different file formats (txt, csv, json)
2. Error Handling
- Try, except blocks
- Handling exceptions and errors gracefully
3. Object-Oriented Programming (OOP)
- Classes and objects
- Inheritance and polymorphism
- Encapsulation
Step 3: Libraries for Data Analysis
1. NumPy
- Understanding arrays and array operations
- Indexing, slicing, and iterating
- Mathematical functions and statistical operations
2. Pandas
- Series and DataFrames
- Reading and writing data (csv, excel, sql, json)
- Data cleaning and preparation
- Merging, joining, and concatenating data
- Grouping and aggregating data
3. Matplotlib and Seaborn
- Data visualization with Matplotlib
- Plotting different types of graphs (line, bar, scatter, histogram)
- Customizing plots
- Advanced visualizations with Seaborn
Step 4: Data Manipulation and Analysis
1. Data Wrangling
- Handling missing values
- Data transformation
- Feature engineering
2. Exploratory Data Analysis (EDA)
- Descriptive statistics
- Data visualization techniques
- Identifying patterns and outliers
3. Statistical Analysis
- Hypothesis testing
- Correlation and regression analysis
- Probability distributions
Step 5: Advanced Topics
1. Time Series Analysis
- Working with datetime objects
- Time series decomposition
- Forecasting models
2. Machine Learning Basics
- Introduction to machine learning
- Supervised vs. unsupervised learning
- Using Scikit-Learn for machine learning
- Building and evaluating models
3. Big Data and Cloud Computing
- Introduction to big data frameworks (e.g., Hadoop, Spark)
- Using cloud services for data analysis (e.g., AWS, Google Cloud)
Step 6: Practical Projects
1. Hands-on Projects
- Analyzing datasets from Kaggle
- Building interactive dashboards with Plotly or Dash
- Developing end-to-end data analysis projects
2. Collaborative Projects
- Participating in data science competitions
- Contributing to open-source projects
👨💻 FREE Resources to Learn & Practice Python
1. https://www.freecodecamp.org/learn/data-analysis-with-python/#data-analysis-with-python-course
2. https://www.hackerrank.com/domains/python
3. https://www.hackerearth.com/practice/python/getting-started/numbers/practice-problems/
4. https://t.me/PythonInterviews
5. https://www.w3schools.com/python/python_exercises.asp
6. https://t.me/pythonfreebootcamp/134
7. https://t.me/pythonanalyst
8. https://pythonbasics.org/exercises/
9. https://t.me/pythondevelopersindia/300
10. https://www.geeksforgeeks.org/python-programming-language/learn-python-tutorial
11. https://t.me/pythonspecialist/33
*React ♥️ for more*
❤9