AIQB
TutorialsOrdinary

I fine-tuned Qwen3.6 on Tinker to read my neighbours’ khata: 98% credit/payment accuracy for $0.38

Source: DEV Community·
Qwen

Summary

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle ...
CategoryAI Tutorials & Practice
TierOrdinary
Published
Indexed by AIQB
SourceDEV Community
AIQB record IDintel-3d669366b728cdfbb0276201
Read original source ↗More Tutorials

Related stories

Matched by category, entity tags and source

TutorialsOrdinary
🔬 J'ai mappé les offres d'emploi public de l'OPT-NC avec le référentiel ESCO à l'aide d'embeddings et de Qwen3-32B-AWQ
❔ Contexte Avant de me lancer de l'organisation du HackAVP : 🏆 #HackAVP, premier...
Source: DEV Community · Qwen
TutorialsOrdinary
From Messy WhatsApp Chits to GST Invoices in 15s — Local AI with Ollama & Qwen 2.5
BahiPilot: The Local-First AI Back Office for Bharat's Wholesalers This is a submission...
Source: DEV Community · Qwen / Ollama
TutorialsOrdinary
Fine-Tuning Qwen3-8B with Tinker: From 50% to 76% Accuracy, and Burning Through My Budget
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle Oktoberfest?...
Source: DEV Community · Qwen
TutorialsOrdinary
How I Built a Fully Local AI Coding Agent with Qwen 3.8, LM Studio, and Pi (No Paid APIs)
What if you could have an AI coding agent that reads your files, writes code, executes commands, and...
Source: DEV Community · Qwen
TutorialsOrdinary
I Distilled a 397B Model Into a 4B One for $1.60. It Now Catches 28 of 33 Park Alerts That Should Stop Your Hike.
A Qwen3.5-4B LoRA trained on Tinker reads all 627 live National Park Service alerts, is graded against the rangers' own labels, and prints one go/no-go trail card a week. Then it stops talking.
Source: DEV Community · Qwen
TutorialsOrdinary
WildQuest: Offline Nature Quests with On-Device Qwen AI
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...
Source: DEV Community · Qwen
TutorialsOrdinary
Multi-Reward RL, Part 3: GDPO + CISPO + REPO-R at 27B, and the Advantage Floor That Stopped Learning
Qwen3.8-27B, 600 steps, 12 reward channels: CISPO, REPO-R and prompt filtering lifted holdout from −0.47 to +1.80, and an advantage floor silently zeroed 96% of the signal.
Source: DEV Community · Qwen
TutorialsOrdinary
Seu classificador de intenções é 12 pontos pior em português: um benchmark de Laya, Strands Decider e embeddings Qwen3
Um benchmark reprodutível de pequenos modelos de decisão e de embeddings para classificar o objetivo do cliente em português do Brasil, e o que uma tradução paralela para o inglês revela sobre o custo do idioma.
Source: DEV Community · Qwen
TutorialsOrdinary
Your intent classifier is 12 points worse in Portuguese: benchmarking Laya, Strands Decider and Qwen3 embeddings
A reproducible benchmark of small choice deciders and embeddings for customer-goal classification in Brazilian Portuguese, plus what a parallel English translation reveals about the cost of language.
Source: DEV Community · Qwen
TutorialsOrdinary
Fine-tuning Qwen2.5-1.5B on a Mac to fix a parroting chatbot (and halve the prompt)
By Georgii Kharlampiiev, Mindscend Our company website is a single chat page backed by a model we...
Source: DEV Community · Qwen