pythonym's profile picture. Follow me for all the latest ML tools and concepts.

MJ

@pythonym

Follow me for all the latest ML tools and concepts.

The Internet should stop making stupid people famous.


MJ reposted

PyTorch 2.9 is now available, introducing key updates to performance, portability, and the developer experience. This release includes a stable libtorch ABI for C++/CUDA extensions, symmetric memory for multi-GPU kernels, expanded wheel support to include ROCm, XPU, and CUDA 13,…

PyTorch's tweet image. PyTorch 2.9 is now available, introducing key updates to performance, portability, and the developer experience.

This release includes a stable libtorch ABI for C++/CUDA extensions, symmetric memory for multi-GPU kernels, expanded wheel support to include ROCm, XPU, and CUDA 13,…

🔥Kangas It is a tool for exploring, analyzing, and visualizing large-scale multimedia data. It provides a straightforward Python API for logging large tables of data, along with an intuitive visual interface for performing complex queries against your dataset. The key…

pythonym's tweet image. 🔥Kangas

It is a tool for exploring, analyzing, and visualizing large-scale multimedia data. 

It provides a straightforward Python API for logging large tables of data, along with an intuitive visual interface for performing complex queries against your dataset.

The key…

🚀 Data distribution shifts after model deployment! A common problem that often occurs after model deployment is Data Distribution Shifts. It refers to the differences between the distribution of data on which a model was trained and the distribution of data it encounters in the…

pythonym's tweet image. 🚀 Data distribution shifts after model deployment!

A common problem that often occurs after model deployment is Data Distribution Shifts. It refers to the differences between the distribution of data on which a model was trained and the distribution of data it encounters in the…

🔥 Text Distance It is a Python library for comparing distance between two or more sequences by many algorithms. Features: - 30+ algorithms - Pure python implementation - Simple usage - More than two sequences comparing - Some algorithms have more than one implementation in one…

pythonym's tweet image. 🔥 Text Distance

It is a Python library for comparing distance between two or more sequences by many algorithms.

Features:
- 30+ algorithms
- Pure python implementation
- Simple usage
- More than two sequences comparing
- Some algorithms have more than one implementation in one…

⚡ Similarity Search across millions of vector embeddings is both computationally and memory-intensive. With Facebook's Faiss, you can optimize the vector search using optimized indexing with compression algorithms. In the video, I've discussed and implemented how to optimize…


🔥 FlashLight It is a fast, flexible machine learning library written entirely in C++. Core features: - Total internal modifiability, including internal APIs for tensor computation. - A small footprint, with the core clocking in at under 10 MB and 20k lines of C++. -…

pythonym's tweet image. 🔥 FlashLight

It is a fast, flexible machine learning library written entirely in C++.

Core features:
- Total internal modifiability, including internal APIs for tensor computation.
- A small footprint, with the core clocking in at under 10 MB and 20k lines of C++.
-…

Donald Trump, as President, is misusing his power to gamble with the Global Economy. #Trump #bitcoin


DMart >> Blinkit and Zepto #DMart


🔥 cuVs All vector databases use algorithms implemented by cuVS. It is a new library mostly derived from the approximate nearest neighbors and clustering algorithms in the RAPIDS RAFT library of machine learning and data mining primitives. It contains the most fully-featured…

pythonym's tweet image. 🔥 cuVs

All vector databases use algorithms implemented by cuVS.

It is a new library mostly derived from the approximate nearest neighbors and clustering algorithms in the RAPIDS RAFT library of machine learning and data mining primitives.

It contains the most fully-featured…

🔥 BytePS - A high-performance and general distributed training framework. - Supports TensorFlow, Keras, PyTorch, and MXNet. - Runs on TCP or RDMA network. - It outperforms existing open-sourced distributed training frameworks by a large margin

pythonym's tweet image. 🔥 BytePS

- A high-performance and general distributed training framework.
- Supports TensorFlow, Keras, PyTorch, and MXNet.
- Runs on TCP or RDMA network.
- It outperforms existing open-sourced distributed training frameworks by a large margin

🔥 Flyte - It is an open-source orchestrator that facilitates building production-grade data and ML pipelines. - It is built for scalability and reproducibility, leveraging Kubernetes as its underlying platform. - With Flyte, user teams can construct pipelines using the Python…

pythonym's tweet image. 🔥 Flyte

- It is an open-source orchestrator that facilitates building production-grade data and ML pipelines.

- It is built for scalability and reproducibility, leveraging Kubernetes as its underlying platform.

- With Flyte, user teams can construct pipelines using the Python…

It is Nvidia's World, we are all just living in it! #Nvidia

pythonym's tweet image. It is Nvidia's World, we are all just living in it!

#Nvidia

🔥 PyG (PyTorch Geometric) PyG (PyTorch Geometric) is a library built upon PyTorch to easily write and train Graph Neural Networks (GNNs) for a wide range of applications related to structured data. It consists of various methods for deep learning on graphs and other irregular…

pythonym's tweet image. 🔥 PyG (PyTorch Geometric)

PyG (PyTorch Geometric) is a library built upon PyTorch to easily write and train Graph Neural Networks (GNNs) for a wide range of applications related to structured data.

It consists of various methods for deep learning on graphs and other irregular…

Never trust a app promoted by ruiling government. Never. #Zoho


🔥 ONNX Open Neural Network Exchange (ONNX) is an open ecosystem that empowers AI developers to choose the right tools as their project evolves. It provides an open-source format for AI models, both deep learning and traditional ML. It defines an extensible computation graph…

pythonym's tweet image. 🔥 ONNX

Open Neural Network Exchange (ONNX) is an open ecosystem that empowers AI developers to choose the right tools as their project evolves.

It provides an open-source format for AI models, both deep learning and traditional ML.

It defines an extensible computation graph…

📢 Highly recommend five AI/ML courses 🚀 AI For Everyone ((DeepLearning.AI/Coursera)):Focus: A great starting point for non-technical audiences to understand AI concepts, applications, and how it impacts society. Key Takeaway: Provides a conceptual understanding of AI without…


🔥 Nanotron It is a library for pretraining transformer models. It provides a simple and flexible API to pretrain models on custom datasets. It is designed to be easy to use, fast, and scalable.

pythonym's tweet image. 🔥 Nanotron

It is a library for pretraining transformer models. It provides a simple and flexible API to pretrain models on custom datasets. It is designed to be easy to use, fast, and scalable.

🔥 DeepSearcher It combines cutting-edge LLMs (OpenAI o3, Qwen3, DeepSeek, Grok 4, Claude 4 Sonnet, Llama 4, QwQ, etc.) and Vector Databases (Milvus, Zilliz Cloud, etc.) to perform search, evaluation, and reasoning based on private data, providing highly accurate answers and a…

pythonym's tweet image. 🔥 DeepSearcher

It combines cutting-edge LLMs (OpenAI o3, Qwen3, DeepSeek, Grok 4, Claude 4 Sonnet, Llama 4, QwQ, etc.) and Vector Databases (Milvus, Zilliz Cloud, etc.) to perform search, evaluation, and reasoning based on private data, providing highly accurate answers and a…

Loading...

Something went wrong.


Something went wrong.