[Alignment training (DPO)] Megatron support for QWEN2.5 series models #183
Description
when will the QWEN2.5 series models support alignment training (RLHF、DPO、OnlineDPO、GRPO) using the Megatron
{{ message }}
when will the QWEN2.5 series models support alignment training (RLHF、DPO、OnlineDPO、GRPO) using the Megatron