ReasoningMila/math_train_gold_qs_all_64_synthetic_soln_480k
Updated
Mila Reasoning
university
AI & ML interests
None defined yet.
models 10
ReasoningMila/hendricks_math_7500_train_synthetic_corr_soln
Updated
ReasoningMila/polIter_qwen2.5_math_1.5B_inst_ppo_MATH_ckpt__iter_0047__epoch_2.00_step_1504
Updated
ReasoningMila/math_synthetic_raw
Updated
ReasoningMila/polIter_qwen2.5_math_inst_1.5B_genppo_MATH_ckpt_iter_0008_epoch_2.00_step_0448
Updated
ReasoningMila/polIter_qwen2.5_math_inst_1.5B_genppo_MATH_ckpt_iter_0008_epoch_2.00_step_0512
Updated
ReasoningMila/ver_gen_partial_ft_model_meta-llama_Llama-32-1B_checkpoint-5634
Text Generation • 1B • Updated • 3 •
ReasoningMila/ver_partial_ft_model_meta-llama_Llama-32-3B_checkpoint-4224
Text Generation • 3B • Updated • 3
ReasoningMila/ver_partial_ft_model_meta-llama_Llama-32-1B_checkpoint-4224
Text Generation • 1B • Updated • 4 •
ReasoningMila/math_partial_ft_model_meta-llama_Llama-32-3B_checkpoint-681
Text Generation • 3B • Updated • 1
datasets 15
ReasoningMila/Training_gen_dataset
Viewer • Updated • 7.5k • 47
ReasoningMila/ServiceNowAI_R1_Distill_SFT_with_problems_and_responses
Viewer • Updated • 1.68M • 1.31k
ReasoningMila/math7500_1_wrong_soln_wrt_human_gold
Viewer • Updated • 6.08k • 4
ReasoningMila/wrong_solutions_dataset_of_30k_verified_qs
Viewer • Updated • 22.4k • 8
ReasoningMila/syn_qs_and_soln_cleaned_0_and_less20_multiple_soln_per_qs_1937545
Viewer • Updated • 1.94M • 67
ReasoningMila/syn_qs_and_soln_cleaned_0_and_less20_1_soln_per_qs_131845
Viewer • Updated • 132k • 5
ReasoningMila/syn_qs_soln_dat_cleaned_1_soln_per_qs_41k
Viewer • Updated • 41.3k • 17
ReasoningMila/Verifier_filtered_datasets
Preview • Updated • 5
ReasoningMila/merged_output_qs_only_exact_dedup_90_cleaned_dataset_morethan10resp_clip16_sorted
Viewer • Updated • 215k • 10
ReasoningMila/merged_output_qs_only_exact_dedup_90_dedup_350k
Viewer • Updated • 217k • 46