Mila Reasoning

ReasoningMila 's models 10

Sort:  Recently updated

ReasoningMila/math_train_gold_qs_all_64_synthetic_soln_480k

Updated Mar 17

ReasoningMila/hendricks_math_7500_train_synthetic_corr_soln

Updated Mar 16

ReasoningMila/polIter_qwen2.5_math_1.5B_inst_ppo_MATH_ckpt__iter_0047__epoch_2.00_step_1504

Updated Feb 10

ReasoningMila/math_synthetic_raw

Updated Feb 7

ReasoningMila/polIter_qwen2.5_math_inst_1.5B_genppo_MATH_ckpt_iter_0008_epoch_2.00_step_0448

Updated Feb 6

ReasoningMila/polIter_qwen2.5_math_inst_1.5B_genppo_MATH_ckpt_iter_0008_epoch_2.00_step_0512

Updated Jan 31

ReasoningMila/ver_gen_partial_ft_model_meta-llama_Llama-32-1B_checkpoint-5634

Text Generation • 1B • Updated Jan 12 • 12

ReasoningMila/ver_partial_ft_model_meta-llama_Llama-32-3B_checkpoint-4224

Text Generation • 3B • Updated Jan 8 • 10

ReasoningMila/ver_partial_ft_model_meta-llama_Llama-32-1B_checkpoint-4224

Text Generation • 1B • Updated Jan 6 • 12

ReasoningMila/math_partial_ft_model_meta-llama_Llama-32-3B_checkpoint-681

Text Generation • 3B • Updated Dec 22, 2024 • 9