This repository is a path-preserving research snapshot for Hausa and Yoruba adaptation experiments based on AIDC-AI/Marco-Nano-Base. It contains model weights, resumable checkpoints, training and evaluation code, logs, and raw LightEval results collected on the Anvil cluster. The directory hierarchy follows the original routinganalysis project so that scripts and recorded paths remain easy to trace. No symbolic links are - finetuning/phase2full/checkpoints/marconanobase/hauLatn100kfull - finetuning/phase2full/checkpoints/marconanobase/yorLatn50kfull - finetuning/phase2full/checkpoints/marconanobase/yorLatn50kexp3trainonlyyorpretrainingcorpustop8experts These directories are preserved in…
Independent publisher
Liang Liang
lylybig8
Models in Library1
Datasets in Library1
Models on Hugging Face—
Followers—
Compare the published evidence
This profile connects the 2 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.
Models
Datasets
This dataset preserves original routinganalysis/... paths for all regular files under the five marconanobase directories whose basename contains danLatn. There are no separately matching regular files. Every file inside the selected directory trees is included. No.gitignore file or checkpoint-name exclusion rule is consulted. The repository stores each path as a separate file. Local ownership, permissions, and timestamps are recorded in the manifests but are not repository filesystem metadata.