Strengths3
- Clear end-to-end pipeline from raw data to published model
- Well-documented README and model card with usage example and explicit bias warnings
- Domain-specific data cleaning steps tailored to the characteristics of the DMM dataset
Tutorial / Demo · Python
turkish-disinfo-rationale
Türkçe iddia → fact-check gerekçe üretici LoRA. Qwen3.6-35B-A3B + Tinker SFT. HF: efekurucay/turkish-disinfo-rationale
What it is
This repository provides an end-to-end pipeline for fine-tuning the Qwen3.6-35B-A3B model using LoRA SFT via the Tinker framework to generate Turkish disinformation rationales, including data cleaning, conversion, training, evaluation, and model publishing.
Merit describes the code at this commit. Later pushes count once the owner rescans. How merit is scored
Where it counts
- NLP & LLMs90%
- Machine Learning60%
- Data Science40%
- MLOps20%
How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.
What the judge found
Read from the project's code at its scored commit.
Limitations
The owner keeps this project's limitations private.
Around it on the NLP & LLMs board
Whole board- 109MESOC-Serapeum-API-oldML Application · Python40.6ImplementationDragan CisicNLP & LLMs
- 110claude-studioAI Developer Tool39.6ImplementationMaster MindNLP & LLMs
- 111turkish-disinfo-rationaleTutorial / Demo · Python38.4ExplorationYahya Efe KuruçayNLP & LLMs
- 112DICEML Application · HTML35.1ExplorationIrine MiltonNLP & LLMs
- 113SmokeBreakML Application · Python34.6ExplorationRickNLP & LLMs
