John Kirchenbauer

jwkirchenbauer's activity

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

updated a dataset 4 days ago

jwkirchenbauer/metamathqa-grouped-split-l3-magpie

Viewer • Updated 4 days ago • 395k • 10

published a dataset 5 days ago

jwkirchenbauer/metamathqa-grouped-split-l3-magpie

Viewer • Updated 4 days ago • 395k • 10

updated 3 datasets 7 days ago

jwkirchenbauer/fictionalqa_reformatted_triviaqa

Viewer • Updated 7 days ago • 16.4k • 31

jwkirchenbauer/fictionalqa_training_splits

Viewer • Updated 7 days ago • 219k • 328

jwkirchenbauer/fictionalqa

Viewer • Updated 7 days ago • 39.2k • 86 • 2

updated a collection 16 days ago

MTP-LM

Collection

Models to accompany research paper on training multi token prediction language models using self-distillation. • 4 items • Updated 7 days ago • 3

updated a collection 23 days ago

MTP-LM

Collection

Models to accompany research paper on training multi token prediction language models using self-distillation. • 4 items • Updated 7 days ago • 3

updated a collection 27 days ago

MTP-LM

Collection

Models to accompany research paper on training multi token prediction language models using self-distillation. • 4 items • Updated 7 days ago • 3

updated a model 27 days ago

jwkirchenbauer/L3-1-8B-Magpie-MTP

8B • Updated 27 days ago • 73

published a model 27 days ago

jwkirchenbauer/L3-1-8B-Magpie-MTP

8B • Updated 27 days ago • 73

updated a model 27 days ago

jwkirchenbauer/Qwen3-4B-Inst-2507-MTP

4B • Updated 27 days ago • 125 • 1

published a model 27 days ago

jwkirchenbauer/Qwen3-4B-Inst-2507-MTP

4B • Updated 27 days ago • 125 • 1

updated a collection 27 days ago

MTP-LM

Collection

Models to accompany research paper on training multi token prediction language models using self-distillation. • 4 items • Updated 7 days ago • 3

updated a dataset 28 days ago

jwkirchenbauer/metamathqa-grouped-split

Viewer • Updated 28 days ago • 395k • 142

published a dataset 28 days ago

jwkirchenbauer/metamathqa-grouped-split

Viewer • Updated 28 days ago • 395k • 142

updated 3 models 28 days ago

jwkirchenbauer/daint_prod_q4_32N128n_12cacdc9_latest

Text Generation • 8B • Updated 28 days ago • 11

jwkirchenbauer/debug_metamath_full_rand_k2-8_ex_valk_baseline_latest

Text Generation • 8B • Updated 28 days ago • 10

jwkirchenbauer/daint_prod_q4_128N512n_fd7261ea

Text Generation • 8B • Updated 28 days ago • 14