Review of AI LLM THUDM/codegeex4-all-9b code generation Its a new 9 billion parameters specialized for code generation. It did not run on a T4. Ran out of GPU memory but ran well on A100 GPU. Need Max output token limit increased depending upon the output size. Also, need hugginface token to download the model from huggingface. It created python code that worked for mendelbrot, julia, and iterated fern, failed on sepienski and koch snowflake. It did very well in creating python code for solving differential equations, including the mechanical vibration problems. One can view the example in this Google Colab notebook https://lnkd.in/gaBkqvVv #AI #LLM #CODE #GENERATION #Python
Javed Alam’s Post
More Relevant Posts
-
AI Engineer | NLP Engineer | Generative AI Engineer| Master's in Data Science & AI from Queen's University, Canada
If you're like me and sometimes run into GPU limitations on your local machine, I Tried a neat workaround to run Ollama in Google Colab, allowing you to leverage Colab's resources for your AI projects. You can find how To set it up Here : https://lnkd.in/deU6-HHY #GenerativeAI #LLM #RAGsystems #ArtificialIntelligence #MachineLearning #DataScience #AIResearch #TechInsights #AIApplications #AICommunity #Ollama #Python
Google Colab
colab.research.google.com
To view or add a comment, sign in
-
Prompt Engineering | No-code Development | Automation | Chatbot Development | Search Engine Optimization (SEO)
🚀 Exploring Non-Euclidean Clustering Algorithms! 🌐 Excited to share my latest project on clustering in non-Euclidean spaces using spherical and hyperbolic distance metrics. Dive into the code and visualizations to see how we can push the boundaries of traditional clustering methods. Check it out on Colab: https://lnkd.in/gY-D6YF3 #DataScience #MachineLearning #Clustering #NonEuclidean #AI #Python
Google Colab
colab.research.google.com
To view or add a comment, sign in
-
Prompt Engineering | No-code Development | Automation | Chatbot Development | Search Engine Optimization (SEO)
🚀 Excited to share my latest project on Multi-dimensional Knot Theory! 🧵 🔍 Project Highlights: * Persistent Homology: Leveraging Gudhi library for topological data analysis. * Machine Learning: Classifying knots using a neural network model. * Visualization: Detailed persistence diagrams for in-depth analysis. Check out the full project and code on Google colab! #DataScience #MachineLearning #Topology #KnotTheory #Python
Google Colab
colab.research.google.com
To view or add a comment, sign in
-
Lectures 10, 11, and 12 Highlights: Advanced AI with Sir Irfan Malik As-salamu alaykum! Today, in our Advanced AI Learning Journey, we are covering three essential lectures with Sir Irfan Malik. In these sessions, we will discuss: - Conditional statements - Loops (while loops and for loops) - User-defined functions in Python - Open Ai To enhance your learning experience, we've prepared a Colab notebook with practical exercises. Check out the link below and follow along with the exercises. 📚 Colab Notebook Link of Lecture 10 https://lnkd.in/d_fNBGFy 📚 Colab Notebook Link of Lecture 11 https://lnkd.in/dA67vN-P 📚 Colab Notebook Link of Lecture 12 https://lnkd.in/dEfsjd5v Let's continue building our Python skills together! #AI #Python #Functions #Loops #ConditionalStatements #LearningJourney #ZeonSolutions #TechSkills #ContinuousLearning
Google Colab
colab.research.google.com
To view or add a comment, sign in
-
Lately, I've been reading a lot about creating Neural Networks with Python and NumPy. The whole process has been fascinating and informative. Below is a Neural Network solving the classic XOR gate problem:
Google Colab
colab.research.google.com
To view or add a comment, sign in
-
Prompt Engineering | No-code Development | Automation | Chatbot Development | Search Engine Optimization (SEO)
Notebook: https://lnkd.in/gyXaJQVv 💀 Proud to present my most recent project: A Python-Based Global Search Optimization Platform (GSOP) That Leads the Industry! 📊 This state-of-the-art notebook features: ✅ Modular design incorporating multiple optimization algorithms ✅ Parallel processing for improved performance ✅ Extensive statistical analysis and benchmarking ✅ Interactive visualizations and experiment configuration ✅ Model persistence for simple sharing and replication This tool can greatly enhance your optimization workflows, regardless of your field of expertise—data science, machine learning, or operations research. Look over the notebook and let me know what you think! How may you use this in your professional life? #MachineLearning #DataScience #Optimization #Python #OpenSource 🐉 If you think this is helpful, please like, comment, and share!
Google Colab
colab.research.google.com
To view or add a comment, sign in
-
On Day 11 of the #Amdari21DaysDataChallenge, I performed data cleaning and exploratory data analysis, revealing intriguing patterns in power generation across the four seasons, with a significant number of rows showing zero power generation. I developed and trained various models, including linear regression, random forest, gradient-boosting regressor, and SVR. The random forest and gradient-boosting models demonstrated promising results, with reasonable mean squared error and mean absolute error. I further optimized these models through hyperparameter tuning, successfully identifying the optimal hyperparameters for improved performance. Below is the link to my workbook👇 https://lnkd.in/eZ55M4TX #Mariam_AlabiAmdariTODDC #DataAnalysis #DataScience #Python #Day11
Google Colab
colab.research.google.com
To view or add a comment, sign in
-
Hello Connections! 😊 Today, I am excited to share the completion of my latest project in the AI field: YouTube Analysis Using Python. 📊🔍 In this project, I delved deep into YouTube's data, leveraging advanced data analytics to uncover key insights and trends through real-time data scraping and analysis. Here’s a glimpse of what I have accomplished: https://lnkd.in/dJipG6Dj #DataScience #MachineLearning #Python #YouTubeAnalytics #AI #trending #ArtificialIntelligence
Google Colab
colab.research.google.com
To view or add a comment, sign in
-
Make Pandas 150X faster with one line of code... ...from NVIDIA. Grab it here: cuDF is a GPU DataFrame library for loading joining, aggregating, filtering, and otherwise manipulating data. Here's how it works: %load_ext cudf.pandas That's it! Try it: https://lnkd.in/dWQepmg8 Download it: https://lnkd.in/dbtW5yV Looking to start using Python for market data analysis? Here's a free Ultimate Guide with everything you need to get started. Join the 1,000s of people who finally started with Python after reading it: https://lnkd.in/eNtRcYHX
Google Colab
colab.research.google.com
To view or add a comment, sign in
-
Data Scientist | JPMorganChase I Machine Learning | Deep Learning | Artificial Intelligence | Generative AI LLMs | Reinforcement Learning
🚀 I just created a new notebook! Did you know the LLM ARENA uses Gradio? 🎨 Gradio is an amazing tool that lets you build a user-friendly web interface for your machine learning models with just a few lines of Python. Here's my notebook that uses Gradio to demo a powerful image captioning model! https://lnkd.in/ezAGPRRx BLIP model -> Bootstrapped Language Image Pretraining #MachineLearning
Google Colab
colab.research.google.com
To view or add a comment, sign in
Professor emeritus at Youngstown State University
4mo