TL;DR shift checkpoints - a DatPySci Collection

DatPySci 's Collections

Weak reward Anthropic-HH

Weak reward TL;DR

TL;DR shift checkpoints

TL;DR shift checkpoints

updated Sep 28, 2024

DatPySci/sft_model_tldr_summarization

Text Generation • Updated Sep 28, 2024 • 10
DatPySci/model_step_32400_tldr_summarization

Text Generation • Updated Sep 28, 2024 • 11
DatPySci/model_step_72000_tldr_summarization

Text Generation • Updated Sep 28, 2024 • 13