work CostGuard Production-grade LLM reliability proxy with cost tracking, circuit breakers, and observability RealDataAgentBench Open-source LLM evaluation framework — 12 frontier models, 1,180+ runs, 39 data science tasks LoRA Fine-tuning of DeepSeek-R1 Mathematical reasoning on a 1.5B model — 98.8% parameter reduction, 2× throughput with Unsloth AI-Assisted Medical Image Diagnosis LLM-powered X-ray interpretation tool using Groq Cloud API and vision models fun
