Dokyoon's picture

Dokyoon

leeloolee

·

Eruly

AI & ML interests

ai

Recent Activity

liked a dataset about 3 hours ago

ArtificialAnalysis/AA-Omniscience-Public

liked a dataset about 16 hours ago

obalcells/hallucination-heads-longfact

reacted to Lyte's post with 🔥 1 day ago

Introducing Nanochat Moroccan Nanochat Moroccan is the first language model family built specifically for Moroccan Darija. This project brings together a small family of models and datasets centered on Darija, with the goal of building something genuinely useful for a language that is still underserved in AI. 1. Models - https://huggingface.co/KandirResearch/Nanochat-Moroccan-Base-0.7B - https://huggingface.co/KandirResearch/Nanochat-Moroccan-Instruct-0.7B-pt-raw - https://huggingface.co/KandirResearch/Nanochat-Moroccan-Instruct-0.7B 2. Data - https://huggingface.co/datasets/Lyte/darija-pretraining-corpus - https://huggingface.co/datasets/Lyte/darija-pretraining-corpus-nanochat - https://huggingface.co/datasets/Lyte/Moroccan-Darija-Instruct-573K - https://huggingface.co/datasets/GemMaroc/TULU-3-50k-darija-english 3. Collection - https://huggingface.co/collections/KandirResearch/nanochat-the-first-moroccan-darija-language-model-family Moroccan Darija is spoken by millions of people, yet it remains underrepresented in language technology. Nanochat Moroccan is a step toward building tools that take the language seriously. You are welcome to try it and chat with it here: https://huggingface.co/spaces/Lyte/Nanochat-Moroccco-Instruct

View all activity

Organizations

leeloolee 's datasets 1

leeloolee/mdpo

Updated Oct 23, 2024 • 11 • 1