南栖

icon location NLP，MultiModal，Human intelligence，Bioinformatics

Results 53 comments of 南栖

Add Amara-o1-7B-Qwen Amara-o2-7B-Qwen to AlpacaEval

@YannDubs

Add Amara-o1-7B-Qwen Amara-o2-7B-Qwen to AlpacaEval

model: https://huggingface.co/Minami-su/Amara-o2-7B-Qwen https://huggingface.co/Minami-su/Amara-o1-7B-Qwen

关于RL训练是否支持LoRA/QLoRA

I'm releasing an open-source framework By combining GRPO + QLoRA + DeepSpeed ZeRO-3,https://github.com/Minami-su/deepspeed-grpo-qlora-vllm