Contents# Small But Powerful# Why Small Language Models Deserve More Attention# Understanding SmolLM3’s Architecture# Setting Up Your Environment# Loading SmolLM3 and Running Your First Inference# Building a Multilingual Support Ticket Router# Adding Tool Calling to SmolLM3# Fine-Tuning SmolLM3 on Domain Data# Conclusion # Small But Powerful  Running a 70B model in production can be expensive, slow, and, for many tasks, unnecessary. If you’re building …

Small Language Models with Hugging Face transformers Library + smolLM3 Read More »

scored 94.3% accuracy. I went back over the terminal output and the confusion matrix more than once. They agreed every time. The number went into my README and onto my CV. It was also wrong. Not by a rounding error, either. The honest figure was 69%. No one caught this for me. It only came …

My Fall-Detection Model Scored 94%, and It Was Lying to Me Read More »

  Contents# Crawling, Not Scraping# 1. Olostep# 2. Firecrawl# 3. ScrapeGraphAI# 4. Scrapling# 5. Crawl4AI# 6. Scrapy# 7. Crawlee# Final Thoughts # Crawling, Not Scraping  People often confuse web scraping with web crawling, but they are not the same thing. Web scraping usually means extracting content from a specific page. You give the tool a URL, and it returns the content from that page in …

7 Best Web Crawling Tools and APIs in 2026 Read More »

pipeline needs the document’s table of contents: retrieval scopes by section, and the chunker cuts on heading boundaries instead of mid-sentence. But some documents don’t have one. A paper exported straight from LaTeX has no native outline and no printed contents page, so there is no toc_df for the pipeline to read. The headings are …

Building Document Structure with Loop Engineering: Recovering a PDF’s Outline from Body Typography for RAG Read More »

  Contents# Dealing With Inference Latency# 1. Implementing Model Quantization# 2. Utilizing Key-Value Caching# L3. everaging Speculative Decoding# 4. Transitioning to Continuous Batching# 5. Pruning and Distilling Your Models# 6. Deploying with Optimized Inference Engines# 7. Optimizing Context and Prompt Management# Stacking Optimizations in Practice # Dealing With Inference Latency  As large language models (LLMs) move from research prototypes into production, engineering teams run into …

7 Approaches to Reduce Inference Latency in Your LLM Workflows Read More »