Julian Minder

jkminder's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a model 11 days ago

jkminder/pretraining-priors-doormail4k-d32-treated-base

Text Generation • 2B • Updated 11 days ago • 168

published a model 11 days ago

jkminder/pretraining-priors-doormail4k-d32-treated-base

Text Generation • 2B • Updated 11 days ago • 168

updated 8 models 18 days ago

jkminder/d20_477m_seed4_sft

Text Generation • 0.5B • Updated 18 days ago • 441

jkminder/d20_477m_seed3_sft

Text Generation • 0.5B • Updated 18 days ago • 455

jkminder/d20_477m_seed1_sft

Text Generation • 0.5B • Updated 18 days ago • 505

jkminder/d20_477m_seed2_sft

Text Generation • 0.5B • Updated 18 days ago • 512

jkminder/d26_973m_seed4_sft

Text Generation • 1.0B • Updated 18 days ago • 535

jkminder/d26_973m_seed3_sft

Text Generation • 1.0B • Updated 18 days ago • 493

jkminder/d26_973m_seed1_sft

Text Generation • 1.0B • Updated 18 days ago • 478

jkminder/d26_973m_seed2_sft

Text Generation • 1.0B • Updated 18 days ago • 467

updated 4 models 19 days ago

jkminder/d12_135m_seed4_sft

Text Generation • 0.1B • Updated 19 days ago • 541

jkminder/d12_135m_seed3_sft

Text Generation • 0.1B • Updated 19 days ago • 519

jkminder/d12_135m_seed1_sft

Text Generation • 0.1B • Updated 19 days ago • 517

jkminder/d12_135m_seed2_sft

Text Generation • 0.1B • Updated 19 days ago • 484

updated 4 models 20 days ago

jkminder/d16_268m_seed4_sft

Text Generation • 0.3B • Updated 20 days ago • 785

jkminder/d16_268m_seed3_sft

Text Generation • 0.3B • Updated 20 days ago • 728

jkminder/d16_268m_seed1_sft

Text Generation • 0.3B • Updated 20 days ago • 725

jkminder/d16_268m_seed2_sft

Text Generation • 0.3B • Updated 20 days ago • 508

updated a collection 22 days ago

Scaling Ladder — 4 sizes, 135M–973M, 200 TPP

Collection

The whole ladder, 200 TPP on ClimbMix; plain GPT (nanochat mechanisms disabled). Bases, then chat-SFTs (_sft). • 56 items • Updated 22 days ago

published a model 22 days ago

jkminder/d12_135m_seed8_sft

Text Generation • 0.1B • Updated 22 days ago • 279