epe-1p-3b-llama3arch-smollm2tok-500B-40n-2048sl-960gbsz-no_bce-util-refl_midtrain_from_epe

Raghav-Singhal/epe-1p-3b-llama3arch-smollm2tok-500B-40n-2048sl-960gbsz-no_bce-util-refl_midtrain_from_epe

Text Generation3B parameterstransformers
Tracked by OpenModelStats since October 5, 2026View on Hugging Face ↗
Downloads 30D
92
Total downloads
92
Gained 7D
—
Gained 30D
—
Likes
0
Rank · tracked models
—
–this week
Parameters
3B
Last source update
Oct 5, 2026

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-10-05. Charts appear as daily observations accumulate.

Overview

epe-1p-3b-llama3arch-smollm2tok-500B-40n-2048sl-960gbsz-no_bce-util-refl_midtrain_from_epe is a text generation model published by Raghav-Singhal. OpenModelStats has tracked the model since Oct 5, 2026, most recently observing it Oct 6, 2026.

Published
Oct 5, 2026
Last updated
Oct 5, 2026
Library
transformers
License
—
Task
Text Generation
Parameters
2,970,135,552
Spaces
—
Derivative models
—
Velocity 7D/day
—
transformerssafetensorsllamatext-generationcausal-lmbfloat16conversationaltext-generation-inferenceendpoints_compatibleregion:us

Similar models

Models similar to epe-1p-3b-llama3arch-smollm2tok-500B-40n-2048sl-960gbsz-no_bce-util-refl_midtrain_from_epe
ModelDL 30D
t0-mt-3b-base-philosophy-sdfP0u4a1,655
vanilla-3b-instructdlab-spp657
Muse-3BMuse-research711
NeoHorse-1-9B-PAROJeethu376
Dayhoff-3b-GR-HM-cmicrosoft577
gidd-unif-3bdvruette420