🦙📚 LlamaTales
Datasets and checkpoints from the paper LlamaTales: Studying the Effects of Developmentally Inspired Training Data on Small Language Models
Viewer • Updated • 2M • 66Note Short stories generated by `nvidia/Llama-3.1-Nemotron-70B-Instruct`.
ivnle/llamatales-jr-70b
Viewer • Updated • 3.56M • 32Note Children's stories generated by `nvidia/Llama-3.1-Nemotron-70B-Instruct`.
ivnle/llamatales-gre
Viewer • Updated • 2.02M • 50Note Short stories generated by `meta-llama/Llama-3.1-8B-Instruct`.
ivnle/llamatales-jr
Viewer • Updated • 3.59M • 51Note Children's stories generated by `meta-llama/Llama-3.1-8B-Instruct`.
ivnle/tinystories
Viewer • Updated • 4.97M • 34Note Source: https://huggingface.co/datasets/roneneldan/TinyStories/blob/main/TinyStories_all_data.tar.gz
ivnle/fineweb
Viewer • Updated • 2.03M • 46Note 1B token sample of FineWeb-Edu https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu Model checkpoints below. Naming format is [training data]-[layers]-[hidden size]-[heads]-[non-embedding parameter count].
ivnle/llamatales_gre_8b-lay8-hs512-hd8-33M
Text Generation • Updated • 12ivnle/llamatales_gre_8b-lay8-hs384-hd6-18M
Text Generation • Updated • 11ivnle/llamatales_gre_8b-lay4-hs384-hd6-9M
Text Generation • Updated • 10ivnle/llamatales_gre_8b-lay4-hs128-hd2-1M
Text Generation • Updated • 11ivnle/llamatales_gre_8b-lay2-hs128-hd2-524K
Text Generation • Updated • 11ivnle/llamatales_gre_8b-lay1-hs128-hd2-262K
Text Generation • Updated • 9ivnle/fineweb-lay8-hs512-hd8-33M
Text Generation • Updated • 17ivnle/fineweb-lay8-hs384-hd6-18M
Text Generation • Updated • 11ivnle/fineweb-lay4-hs384-hd6-9M
Text Generation • Updated • 10ivnle/fineweb-lay4-hs128-hd2-1M
Text Generation • Updated • 8ivnle/fineweb-lay2-hs128-hd2-524K
Text Generation • Updated • 15ivnle/fineweb-lay1-hs128-hd2-262K
Text Generation • Updated • 11ivnle/llamatales_jr_8b-lay8-hs512-hd8-33M
Text Generation • Updated • 256ivnle/llamatales_jr_8b-lay8-hs384-hd6-18M
Text Generation • Updated • 13ivnle/llamatales_jr_8b-lay4-hs384-hd6-9M
Text Generation • Updated • 10ivnle/llamatales_jr_8b-lay4-hs128-hd2-1M
Text Generation • Updated • 12ivnle/llamatales_jr_8b-lay2-hs128-hd2-524K
Text Generation • Updated • 8ivnle/llamatales_jr_8b-lay1-hs128-hd2-262K
Text Generation • Updated • 8ivnle/tinystories-lay8-hs512-hd8-33M
Text Generation • Updated • 10ivnle/tinystories-lay8-hs384-hd6-18M
Text Generation • Updated • 11ivnle/tinystories-lay4-hs384-hd6-9M
Text Generation • Updated • 8ivnle/tinystories-lay4-hs128-hd2-1M
Text Generation • Updated • 9ivnle/tinystories-lay2-hs128-hd2-524K
Text Generation • Updated • 9ivnle/tinystories-lay1-hs128-hd2-262K
Text Generation • Updated • 11