Tiny llm ablation - a d0rj Collection

d0rj 's Collections

Tiny llm ablation

t5gemma-2 speculators

Summarization models

Vision datasets

CoT translated or adapted

Instruct datasets in Russian

Math Instruct datasets in Russian

Instruct preference datasets in Russian

Tiny llm ablation

updated 2 days ago

Small language-model ablations trained on FineWeb-Edu, with evaluation confidence intervals and TensorBoard logs.