Freelancers using JinjaFreelancers using Jinja
Cover image for Your first fine-tune should teach
Your first fine-tune should teach you the whole loop. I walk through it with Unsloth: data → baseline → training → evaluation → local model → Python. Including a mistake I made—and why a completed training run doesn't mean you have a better model. Full tutorial below 👇 https://youtu.be/YxXBojdD1as
0
334
Cover image for FlowSynth — AI-powered multi-agent research
FlowSynth — AI-powered multi-agent research pipeline. Built with FastAPI + LangGraph, it orchestrates 6 AI agents (Orchestrator → Researcher → Analyst → Writer → Reviewer → Finalizer) that research any topic, write articles, and auto-revise based on quality scores. Uses Groq LLMs, DuckDuckGo for web search, Neon PostgreSQL for persistence, JWT auth, and deploys on Render.
1
88