--- title: "#pytorch articles | Hashnode" description: "Explore 332 articles tagged #pytorch on Hashnode. Tutorials, guides, and how-tos from the community." url: "https://hashnode.com/tag/pytorch" --- Tag # #pytorch 332 posts · 239 followers [Michał Z](https://hashnode.com/@sixfingers) · [8h ago](https://hashnode.com/posts/toktumi-1-en/6af4d9f763e3e8f3d91c7e69) ### [How to Build a Large Language Model from Scratch? Toktumi 1.0 – Part 1/3](https://sixfingers.hashnode.dev/toktumi-1-en?utm_source=hashnode&utm_medium=feed) Toktumi 1.0 – a Polish-language LLM based on GPT-2. From web scraping to a working model. 27 min read · [sixfingers.hashnode.dev](https://sixfingers.hashnode.dev/toktumi-1-en?utm_source=hashnode&utm_medium=feed) [Michał Z](https://hashnode.com/@sixfingers) · [8h ago](https://hashnode.com/posts/toktumi-2-en/6af4da49e9132b8921350837) ### [How to Build a Large Language Model from Scratch? Toktumi 2.0 – Part 2/3](https://sixfingers.hashnode.dev/toktumi-2-en?utm_source=hashnode&utm_medium=feed) Toktumi 2.0 – a Polish-language LLM based on GPT-2. How to learn from the first training and do it better. 24 min read · [sixfingers.hashnode.dev](https://sixfingers.hashnode.dev/toktumi-2-en?utm_source=hashnode&utm_medium=feed) [Logit Solutions AI](https://hashnode.com/@logitsolutionsai) · [2d ago](https://hashnode.com/posts/batch-normalization-visually-the-reset-that-keeps-deep-networks-steady/6af200bd3bb56a980ff1851a) ### [Batch normalization, visually: the reset that keeps deep networks steady](https://logitsolutionsai.hashnode.dev/batch-normalization-visually-the-reset-that-keeps-deep-networks-steady?utm_source=hashnode&utm_medium=feed) Deep Learning, Visually #20 Watch the Short: youtube.com/shorts/yYxpjlvW69s Why the numbers drift A deep network is a chain of layers. Each layer takes a weighted sum of the activations from the layer 5 min read · [logitsolutionsai.hashnode.dev](https://logitsolutionsai.hashnode.dev/batch-normalization-visually-the-reset-that-keeps-deep-networks-steady?utm_source=hashnode&utm_medium=feed) [Shakil Ahmed](https://hashnode.com/@shakillinit) · [Nov 2](https://hashnode.com/posts/i-possessed-an-llm-by-editing-its-hidden-layers-then-exorcised-it/6aeb9bd739dfe94bfac683ed) ### [I possessed an LLM by editing its hidden layers, then exorcised it](https://build-mcp-with-ai.hashnode.dev/i-possessed-an-llm-by-editing-its-hidden-layers-then-exorcised-it?utm_source=hashnode&utm_medium=feed) Activation steering on Qwen 2.5 7B, an exorcist that doesn't need to know the dose, and the day my model graded itself too kindly 5 min read · [build-mcp-with-ai.hashnode.dev](https://build-mcp-with-ai.hashnode.dev/i-possessed-an-llm-by-editing-its-hidden-layers-then-exorcised-it?utm_source=hashnode&utm_medium=feed) [Waqas Shahid](https://hashnode.com/@practicaldevblog) · [Nov 1](https://hashnode.com/posts/pytorch-explained-machine-learning-you-can-watch-learn/6ae735c50acd2a9e87cb39ab) ### [PyTorch Explained: Machine Learning You Can Watch Learn](https://practicaldevblog.hashnode.dev/pytorch-explained-machine-learning-you-can-watch-learn?utm_source=hashnode&utm_medium=feed) TensorFlow showed one way to train a model, with layers stacked and compiled. PyTorch, released by Meta's AI research lab in 2016, takes a more hands-on approach: you write ordinary Python, tensors tr 3 min read · [practicaldevblog.hashnode.dev](https://practicaldevblog.hashnode.dev/pytorch-explained-machine-learning-you-can-watch-learn?utm_source=hashnode&utm_medium=feed) [Sanskriti Harmukh](https://hashnode.com/@sharmukh) · [Oct 29](https://hashnode.com/posts/building-a-pytorch-container-image/6ae3788fbb9a014da20ea4c7) ### [Building a PyTorch Container Image](https://vultr.hashnode.dev/building-a-pytorch-container-image?utm_source=hashnode&utm_medium=feed) Build a PyTorch container image from source for CPU or GPU systems and push it to a container registry. 5 min read · [vultr.hashnode.dev](https://vultr.hashnode.dev/building-a-pytorch-container-image?utm_source=hashnode&utm_medium=feed) [ZyVOP](https://hashnode.com/@zyvop) · [Oct 25](https://hashnode.com/posts/i-built-the-smallest-llm-i-could-to-understand-how-they-work-c49fr/6adde001a8cddc47e4d2bb5a) ### [I Built the Smallest LLM I Could to Understand How They Work](https://blog.zyvop.com/i-built-the-smallest-llm-i-could-to-understand-how-they-work-c49fr?utm_source=hashnode&utm_medium=feed) A hands-on walkthrough of a ~108k-parameter character-level GPT in under 200 lines of PyTorch, with the full code included. 12 min read · [blog.zyvop.com](https://blog.zyvop.com/i-built-the-smallest-llm-i-could-to-understand-how-they-work-c49fr?utm_source=hashnode&utm_medium=feed) [Subhojeet Chanda](https://hashnode.com/@subhojeetchanda) · [Oct 23](https://hashnode.com/posts/why-supervised-fine-tuning-fails-against-prompt-injection-co-evolving-llm-defenses-with-multi-agent-rl-mappo/6adba9bf23d497b203266f7a) ### [Why Supervised Fine-Tuning Fails Against Prompt Injection: Co-Evolving LLM Defenses with Multi-Agent RL (MAPPO)](https://subhojeetchanda.hashnode.dev/why-supervised-fine-tuning-fails-against-prompt-injection-co-evolving-llm-defenses-with-multi-agent-rl-mappo?utm_source=hashnode&utm_medium=feed) The Problem: Static Defenses Lose to Adaptive Attackers Most teams defend Large Language Models (LLMs) against prompt-injection and jailbreak attacks using Supervised Fine-Tuning (SFT) on a static dat 3 min read · [subhojeetchanda.hashnode.dev](https://subhojeetchanda.hashnode.dev/why-supervised-fine-tuning-fails-against-prompt-injection-co-evolving-llm-defenses-with-multi-agent-rl-mappo?utm_source=hashnode&utm_medium=feed) [Nitesh Kumar Tudu](https://hashnode.com/@nitesh000) · [Oct 23](https://hashnode.com/posts/amd-and-intel-just-ended-the-x86-ai-inference-war-here-s-what-python-devs-need-to-know/6adb21292f09c17905a0032a) ### [AMD and Intel Just Ended the x86 AI Inference War — Here's What Python Devs Need to Know](https://blog.thecodingant.in/amd-and-intel-just-ended-the-x86-ai-inference-war-here-s-what-python-devs-need-to-know?utm_source=hashnode&utm_medium=feed) AMD just merged ZenDNN into Intel's oneDNN, making PyTorch x86 inference consistent across all vendors. What it means for devs building AI features. 6 min read · [blog.thecodingant.in](https://blog.thecodingant.in/amd-and-intel-just-ended-the-x86-ai-inference-war-here-s-what-python-devs-need-to-know?utm_source=hashnode&utm_medium=feed) [Mene-Ejegi Ogbemi](https://hashnode.com/@ogbemi-ejegi) · [Oct 21](https://hashnode.com/posts/what-is-model-distillation-a-guide-for-developers/6ad9087ef5ddaeeade835143) ### [What Is Model Distillation? A Guide for Developers](https://freecodecamp.org/news/what-is-model-distillation-a-guide-for-developers?utm_source=hashnode&utm_medium=feed) Over time, knowledge has been passed down in various forms. Before writing was invented in ancient Mesopotamia (modern-day Iraq), laws, history, myths, songs, and other information were all transferre 19 min read · [freecodecamp.org](https://freecodecamp.org/news/what-is-model-distillation-a-guide-for-developers?utm_source=hashnode&utm_medium=feed)