This collection includes a refined dataset of Snappfood comments and a model trained on it.
Muhammad Ayoubi
IRI2070
AI & ML interests
🔧 Fine-Tuning Models, 🔄 Transfer Learning, 📊 Dataset Engineering, 📝 Data Annotation, 📚 NLP Research, 🧠 Language Models, 📖 Paper Reading, 💡 Prompt Engineering
Recent Activity
liked
a Space
2 days ago
selfit-camera/Omni-Image-Editor
liked
a model
2 days ago
facebook/MobileLLM-R1-140M
liked
a model
2 days ago
HuggingFaceTB/SmolLM2-360M-Instruct
Organizations
This collection includes a dedicated model and dataset for rules for accepting or rejecting Iranian company names.
-
IRI2070/legal-names-cross-encoder-dataset
Viewer • Updated • 110k • 72 -
IRI2070/legal-names-validation-rules-classifier
Text Classification • 0.4B • Updated • 84 -
IRI2070/legal-names-bi-encoder-dataset
Viewer • Updated • 341k • 17 -
IRI2070/tooka-sbert-large-v2-legal-names-bi-encoder
Sentence Similarity • 0.4B • Updated • 9
This collection includes a refined dataset of Snappfood comments and a model trained on it.
This collection includes a dedicated model and dataset for rules for accepting or rejecting Iranian company names.
-
IRI2070/legal-names-cross-encoder-dataset
Viewer • Updated • 110k • 72 -
IRI2070/legal-names-validation-rules-classifier
Text Classification • 0.4B • Updated • 84 -
IRI2070/legal-names-bi-encoder-dataset
Viewer • Updated • 341k • 17 -
IRI2070/tooka-sbert-large-v2-legal-names-bi-encoder
Sentence Similarity • 0.4B • Updated • 9
This collection is a set of proprietary Persian address models developed using government and non-government data.