Published inAI AdvancesRunning Large Language Models (LLMs) on CPU using llama.cppLearn how to download, run models interactively, use them in Python, and expose them as REST APIs6d ago26d ago2
Published inAI AdvancesAdvanced Chainlit: Building Responsive Chat Apps with DeepSeek R1, LM Studio, and OllamaLearn to Stream LLM Responses, Handle Interruptions, Manage Parallel User Requests, and Isolate Client Sessions in ChainlitFeb 3Feb 3
Published inAI AdvancesUnderstanding Model DistillationLearn what model distillation is and how it works by building one yourselfFeb 14Feb 14
Published inAI AdvancesOptimizing Hugging Face Model LoadingLearn How to Change the Cache Directory, Quantize Models, Use Mixed-Precision, and MoreJan 30Jan 30
Published inAI AdvancesIntegrating DeepSeek into your Python ApplicationsLearn how to use the DeepSeek chat and reasoning models in your Python applications using Ollama, Hugging Face, and the DeepSeek APIJan 276Jan 276
Published inAI AdvancesServer-Side AI Inferencing Made Easy: A Guide to Hugging Face EndpointDiscover how to leverage Hugging Face’s hosted models for seamless, server-side inferencing — no local setup requiredJan 261Jan 261
Published inAI AdvancesBuilding a Chat Application with Image Captioning and Visual Q&A FeaturesLearn How to Create an Interactive Chat UI Using ChainlitJan 235Jan 235
Published inAI AdvancesUsing PandasAI to Query your DataFrames using Natural LanguageLearn how to use AI to query your data without needing to write Pandas codeJan 22Jan 22
Published inAI AdvancesBuilding Chat UI using ChainlitLeveraging Chainlit to Build Powerful and Customizable Chat ApplicationsJan 213Jan 213
Published inAI AdvancesTips and Tricks for Using OllamaLearn how to change the models folder, configure and use the REST API, and moreJan 213Jan 213