kamilburda/qwen35-9b-hyperproof-dapo-native-reasoning-8k-gradient-reasoning Updated about 6 hours ago
kinit/stepwise_eq_sft_model_multitask_2cores_single_data_source_dpo Text Generation • Updated May 31 • 6
kinit/stepwise_eq_sft_model_multitask_2cores_single_data_source_dpo Text Generation • Updated May 31 • 6