This repository preserves Nemotron-CC D004 inputs, data and resume indexes, native training checkpoints, and validation outputs. Each checkpoint and validation directory retains its own run or attempt identity so outputs from different weights are not combined. This archive section maps six seed-42 GGLR ablations and nine seed-42/43/44 evaluations for GGLR, Sign Original, and Sign Normalized. The listed D004 validations use the step-23,564 weights and each records 100,638,720 shifted targets. Validation directory names encode 4gpu-b48 where that suffix is present. GGLR seed 42 is the rerun-07 run, and the centroid-driven-weight-update-only ablation is rerun-02. These identities are kept…
Independent publisher
BarryG
B4RryG
Efficient Model, MoE, Linear Attention
Models in Library0
Datasets in Library1
Models on Hugging Face—
Followers—
Compare the published evidence
This profile connects the 1 model and dataset record 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.