Small language-model ablations trained on FineWeb-Edu, with evaluation confidence intervals and TensorBoard logs.
Dmitry Balobin PRO
d0rj
AI & ML interests
NLP and 🥴 tensors
Recent Activity
liked a model about 11 hours ago
CohereLabs/tiny-aya-global updated a dataset 1 day ago
d0rj/anekdot published a dataset 1 day ago
d0rj/anekdotOrganizations
models 32
d0rj/t5-dense-55M-base
Text Generation • 54.8M • Updated • 235
d0rj/q-mod-51M-base
Text Generation • 50.9M • Updated • 110
d0rj/zarya-51M-base
Text Generation • 50.9M • Updated • 125
d0rj/q-t5-tied-37M-base
Text Generation • 37.4M • Updated • 159
d0rj/q-t5-tied-58M-base
Text Generation • 57.7M • Updated • 168
d0rj/q-latent-moe-52M-A35M-base
Text Generation • 51.6M • Updated • 158
d0rj/q-latent-moe-93M-A52M-base
Text Generation • 92.9M • Updated • 194
d0rj/diffusion-51M-base-v1-failed
Fill-Mask • 51.4M • Updated • 43
d0rj/q-moe-51M-A33M-base
Text Generation • 50.9M • Updated • 209
d0rj/q-moe-98M-A51M-base
Text Generation • 98.1M • Updated • 225
datasets 59
d0rj/anekdot
Viewer • Updated • 975k • 67
d0rj/chgk
RL Environment • Updated • 474k • 15 • 2
d0rj/mathematics_dataset
RL Environment • Updated • 125M • 640 • 3
d0rj/text_meme
Viewer • Updated • 8.58k • 50 • 1
d0rj/ROMB-1.0
Viewer • Updated • 2.55k • 51 • 1
d0rj/ilibrary
Viewer • Updated • 4.54k • 10
d0rj/proverbs-idioms-ru-en-de
Viewer • Updated • 407 • 25
d0rj/russian-synonyms
Viewer • Updated • 225k • 25 • 3
d0rj/muInstruct-ru
Viewer • Updated • 1.79k • 18 • 1
d0rj/R1-Distill-SFT_v1-ru
Viewer • Updated • 620k • 29 • 1