Small language-model ablations trained on FineWeb-Edu, with evaluation confidence intervals and TensorBoard logs.
🤝 Open to Collab
Dmitry Balobin
d0rj
AI & ML interests
NLP and 🥴 tensors.
MIPT PhD student 💙
Recent Activity
liked a dataset about 10 hours ago
openbmb/UltraData-SFT-Agent-2609 liked a model 1 day ago
convaiinnovations/laya updated a collection 2 days ago
Tiny llm ablationOrganizations
models 22
d0rj/diffusion-51M-base
Other • 51.4M • Updated • 10
d0rj/q-prefixlm-51M-base
Text Generation • 50.9M • Updated • 2
d0rj/looped-51M-base
Text Generation • 50.9M • Updated • 189
d0rj/t5-moe-55M-base
Text Generation • 54.9M • Updated • 378
d0rj/q-51M-base
Text Generation • 50.9M • Updated • 135
d0rj/GigaChat3-10B-A1.8B.dspark-large-dev
0.6B • Updated • 60
d0rj/GigaChat3-10B-A1.8B.dspark-base-dev
0.5B • Updated • 56
d0rj/t5gemma-2-1b-1b.dspark-base
0.5B • Updated • 17
d0rj/t5gemma-2-1b-1b.dspark-large
0.6B • Updated • 13
d0rj/t5gemma-2-1b-1b.dflare-large
0.5B • Updated • 7
datasets 57
d0rj/ROMB-1.0
Viewer • Updated • 2.55k • 142 • 1
d0rj/ilibrary
Viewer • Updated • 4.54k • 11
d0rj/mathematics_dataset
Viewer • Updated • 125M • 192 • 3
d0rj/proverbs-idioms-ru-en-de
Viewer • Updated • 407 • 38
d0rj/russian-synonyms
Viewer • Updated • 225k • 20 • 3
d0rj/muInstruct-ru
Viewer • Updated • 1.79k • 26 • 1
d0rj/R1-Distill-SFT_v1-ru
Viewer • Updated • 620k • 21 • 1
d0rj/Text_Guided_Image_Editing-ru
Viewer • Updated • 956 • 16
d0rj/text_meme
Viewer • Updated • 6.24k • 33 • 1
d0rj/Electrical-engineering-ru
Viewer • Updated • 1.13k • 27 • 3