Tristan/llama3.2_piqa_custom_splits_sft_broad_1e-5_lr1e-5_wd0.001_ep5_piqa_custom_splits Text Generation • 1B • Updated Sep 30 • 3
Tristan/llama3.2_piqa_custom_splits_sft_broad_1e-5_lr1e-5_wd0.001_ep10_piqa_custom_splits Text Generation • 1B • Updated Sep 30 • 3
Tristan/llama3.2_piqa_custom_splits_sft_broad_1e-5_lr1e-5_wd0.0001_ep10_piqa_custom_splits Text Generation • 1B • Updated Sep 30 • 5
Tristan/llama3.2_piqa_custom_splits_sft_broad_1e-5_lr1e-5_wd0.0001_ep5_piqa_custom_splits Text Generation • 1B • Updated Sep 30 • 3
Tristan/llama3.2_piqa_custom_splits_sft_broad_1e-5_lr1e-5_wd0.0001_ep1_piqa_custom_splits Text Generation • 1B • Updated Sep 28 • 4
Tristan/llama3.2_piqa_custom_splits_sft_broad_lr1e-6_wd0.0001_ep10_piqa_custom_splits Text Generation • 1B • Updated Sep 28 • 4
Tristan/sft_test_llama3.2_5e-6_5e-5_lr5e-5_wd0.001_ep5_arc_easy Text Generation • 1B • Updated Sep 28 • 3
Tristan/sft_test_llama3.2_5e-6_5e-5_lr5e-6_wd0.001_ep5_arc_easy Text Generation • 1B • Updated Sep 28 • 3
Tristan/sft_test_llama3.2_5e-6_5e-5_lr5e-6_wd0.0001_ep1_arc_easy Text Generation • 1B • Updated Sep 28 • 4
Tristan/sft_test_llama3.2_broad_coverage_lr1e-5_wd0.0001_ep10_arc_easy Text Generation • 1B • Updated Sep 25 • 4
Tristan/sft_test_llama3.2_broad_coverage_lr1e-5_wd0.0001_ep5_arc_easy Text Generation • 1B • Updated Sep 25 • 4
Tristan/sft_test_llama3.2_broad_coverage_lr1e-5_wd0.0001_ep1_arc_easy Text Generation • 1B • Updated Sep 25 • 4
Tristan/sft_test_llama3.2_broad_coverage_lr1e-6_wd0.0001_ep10_arc_easy Text Generation • 1B • Updated Sep 25 • 4
Tristan/sft_test_arc_easy_broader_lr1e-5_wd0.0001_ep5_arc_easy Text Generation • 0.6B • Updated Sep 25 • 1
Tristan/sft_test_arc_easy_broader_lr1e-5_wd0.001_ep10_arc_easy Text Generation • 0.6B • Updated Sep 25 • 5
Tristan/sft_test_arc_easy_broader_lr1e-5_wd0.001_ep5_arc_easy Text Generation • 0.6B • Updated Sep 25 • 1
Tristan/sft_test_arc_easy_broader_lr1e-5_wd0.01_ep1_arc_easy Text Generation • 0.6B • Updated Sep 24 • 3
Tristan/sft_test_arc_easy_broader_lr1e-6_wd0.0001_ep10_arc_easy Text Generation • 0.6B • Updated Sep 24 • 2
Tristan/llama3.2_arc_easy_sft_lr1e-6_wd0.0001_ep10_arc_easy Text Generation • 1B • Updated Sep 22 • 1
Tristan/qwen3_sft_meta_sft_arc_easy_lr1e-6_wd0.0001_ep10_arc_easy Text Generation • 0.6B • Updated Sep 8 • 11
Tristan/sft_qwen3_lambada_it_custom_splits_lr1e-6_wd0.0001_ep10_lambada_openai_mt_it_custom_splits Text Generation • 0.6B • Updated Sep 6 • 11
Tristan/sft_qwen3_lambada_es_custom_splits_lr1e-6_wd0.0001_ep10_lambada_openai_mt_es_custom_splits Text Generation • 0.6B • Updated Sep 6 • 12
Tristan/sft_qwen3_lambada_fr_custom_splits_lr1e-6_wd0.0001_ep10_lambada_openai_mt_fr_custom_splits Text Generation • 0.6B • Updated Sep 6 • 11
Tristan/sft_qwen3_lambada_de_custom_splits_lr1e-6_wd0.0001_ep10_lambada_openai_mt_de_custom_splits Text Generation • 0.6B • Updated Sep 6 • 13
Tristan/sft_qwen3_lambada_en_custom_splits_lr1e-6_wd0.0001_ep10_lambada_openai_mt_en_custom_splits Text Generation • 0.6B • Updated Sep 6 • 11
Tristan/sft_qwen3_piqa_custom_splits_lr1e-6_wd0.001_ep10_piqa_custom_splits Text Generation • 0.6B • Updated Sep 6 • 11