Posts

• Feb 4, 2025 L1 and L2 norms
• Feb 1, 2025 Checking out Moondream
• Jan 30, 2025 Sharing tensors
• Jan 21, 2025 Is a vector space a Euclidean space?
• Jan 16, 2025 What are matrices doing, again?
• Dec 2, 2024 What is a token?
• Oct 15, 2024 Understanding vector databases (with Chroma)
• Sep 28, 2024 Some Keras snippets
• Sep 11, 2024 Profiling CUDA Calls
• Sep 3, 2024 What is a tensor?
• Aug 30, 2024 Computing logic gates with perceptrons
• Aug 28, 2024 Prompting Tips
• Aug 26, 2024 Training, validation, and test datasets
• Aug 12, 2024 Debugging and monitoring Ollama usage
• Jul 29, 2024 LLM inference as a service
• Jul 26, 2024 Download .gguf models from Ollama library
• Jul 22, 2024 Local ChatGPT-like UI (Open WebUI)
• Jul 19, 2024 Deep learning on Arc A770 + Ubuntu 22.04
• Jul 3, 2024 Deep learning on RX 7600 + Ubuntu 22.04
• Jun 29, 2024 Why GPUs are faster than CPUs
• Jun 24, 2024 Safetensors vs GGUF
• Jun 16, 2024 A heretical theory no longer
• Jun 15, 2024 Understanding Advance Vector Extensions (AVX)
• Jun 14, 2024 Running custom GGUF models with Ollama