arxiv:2601.01075
Hansen Lillemark
hlillemark
AI & ML interests
None yet
Organizations
models 21
hlillemark/all_tasks_combined_8b_sft_more_epochs
Text Generation • 8B • Updated
• 3
hlillemark/all_tasks_combined_70b_lora_more_epochs
Updated
hlillemark/all_tasks_combined_8b_sft
Text Generation • 8B • Updated
hlillemark/all_tasks_combined_70b_lora
Updated
hlillemark/llama3_70b_lora_combined_mc_filtered
Updated
hlillemark/combined_sft_mc_filtered
Text Generation • 8B • Updated
• 1
hlillemark/sft_mc_filtered
Updated
hlillemark/llama3_70b_lora_sft_mc_filtered
Updated
hlillemark/sft_lora_filtered
Updated
hlillemark/llama3_8b_sft_mc_filtered
Text Generation • 8B • Updated
• 1
datasets 35
hlillemark/mc_combined_sa_ma_dataset
Viewer
• Updated
• 2.23k • 43
hlillemark/c4_llama_packed_seqlen256
Viewer
• Updated
• 322M • 25
hlillemark/c4_t5_corrupted_seqlen256
Viewer
• Updated
• 650M • 46
hlillemark/c4_llama_packed_seqlen256_tiny
Viewer
• Updated
• 233k • 21
hlillemark/c4_t5_corrupted_seqlen256_tiny
Viewer
• Updated
• 196k • 15
hlillemark/flores200_devtest_mt5-3b-flores200-packed
Viewer
• Updated
• 500k • 11
hlillemark/flores200_devtest_mt5-3b-flores200-baseline
Viewer
• Updated
• 500k • 26
hlillemark/c4_t5_pretrain
Viewer
• Updated
• 180M • 50
hlillemark/flores200_devtest_mt5-3b-flores200-scaffold
Viewer
• Updated
• 500k • 11
hlillemark/flores200_devtest_mt5-1b-flores200-packed
Viewer
• Updated
• 500k • 10