hubnemo/foo
11.5 MB
Marian Tietz
hubnemo
AI & ML interests
None yet
Recent Activity
updated a bucket about 20 hours ago
peft-internal-testing/metamathqa-checkpoints upvoted an article about 22 hours ago
Security incident disclosure — July 2026 updated a dataset 19 days ago
peft-internal-testing/benchmark-graveyardOrganizations
Articles 1
Article
78
Beyond LoRA: Can you beat the most popular fine-tuning technique?
models 206
hubnemo/best-lora-ever
Text Generation • Updated • 2
hubnemo/llama-3.2b-metamathqa-lora64
Text Generation • Updated • 3
hubnemo/so101_sort_cubes_no_top_smolvla_lora_main_rank64_bs32_lr1e-3_steps10000_schedulerdecaylr1e-4
Robotics • Updated • 7
hubnemo/so101_sort_cubes_no_top_smolvla_lora_rank64_bs32_lr1e-3_steps10000_schedulerdecaylr1e-4
Robotics • Updated • 5
hubnemo/libero_spatial_smolvla_lora_alladapter4real_rank64_bs32_lr1e-3_steps100000_schedulerdecaylr1e-4
Robotics • Updated • 2
hubnemo/libero_spatial_smolvla_lora_alladapter4real_rank64_bs32_lr1e-3_steps100000_schedulerdecaylr1e-3
Robotics • Updated • 4
hubnemo/libero_spatial_smolvla_lora_alladapter_rank64_bs32_lr1e-3_steps100000_schedulerdecaylr1e-3
Robotics • Updated • 5
hubnemo/libero_spatial_smolvla_lora_rank64_bs32_lr1e-2_steps100000_schedulerdecaylr1e-3
Robotics • Updated • 3
hubnemo/libero_spatial_smolvla_baseline_pretrained_bs32_lr1e-4_steps100000
Robotics • 0.5B • Updated • 7
hubnemo/libero_spatial_smolvla_baseline_documentation_bs32_lr1e-3_steps100000
Robotics • 0.5B • Updated • 3
datasets 7
hubnemo/eval_cube_out_of_box_il
Viewer • Updated • 1.96k • 16
hubnemo/cube_out_of_box_dataset
Viewer • Updated • 6.54k • 20
hubnemo/so101_sort_cubes
Viewer • Updated • 72.3k • 31
hubnemo/so101_sort
Viewer • Updated • 18.8k • 33
hubnemo/so101_matchbox_reward_fpv_less_bias
Viewer • Updated • 9.03k • 18
hubnemo/so101_matchbox_reward_fpv
Viewer • Updated • 6.6k • 16 • 1
hubnemo/so101_matchbox_reward
Viewer • Updated • 20 • 21