Deep Learning
17 articles10 articles
- Prompt Caching: Paying Once for the Prefix that Every Request Repeats Deep Learning
- Training LLMs on a Budget: LoRA, QLoRA, and LoftQ Deep Learning
- Same Ruler, Smarter Placement: GPTQ Deep Learning
- Slope and Curvature: A Practical Guide to the Jacobian and Hessian Deep Learning
- Same Ruler, Smarter Placement: AWQ Deep Learning
- Packing Intelligence into Fewer Bits: Non-Linear Quantization in LLMs Deep Learning
- A Practical Introduction to LLM Quantization and Linear Mapping Deep Learning
- Decoding RAG Evaluation: When Your Pipeline Fails, Who is to Blame? Deep Learning
- KV Cache: The Trick That Lets LLMs Remember Without Recomputing Deep Learning
- Demystifying LLM Temperature: The Math Behind the Magic of Token Sampling Deep Learning
7 articles
- Word Embeddings: From SVD to Word2Vec Deep Learning
- RNNs, LSTMs, and GRUs: Backpropagation Through Time and Vanishing Gradients Deep Learning
- Regularization in Deep Networks: Weight Decay, Dropout, Early Stopping, and Batch Norm Deep Learning
- Weight Initialization and Layer Normalization: Keeping Deep Signals Stable Deep Learning
- Backpropagation and Optimizers: From SGD to Adam and AdamW Deep Learning
- Activation Functions: From Sigmoid to GELU, and Why Gradients Vanish Deep Learning
- From Boring to Brilliant: A Guide to LLM Sampling Techniques Deep Learning