Guang Yang
Guang Yang
> Hi both, this might be due to the inference difference between CodeT5+ 220M/770M and 2B/6B/16B models. The former models are pretrained from scratch while the latter group of models...
> Hi both, this might be due to the inference difference between CodeT5+ 220M/770M and 2B/6B/16B models. The former models are pretrained from scratch while the latter group of models...
您好，链接又失效了，能再更新下嘛？
> hi [@shimmyshimmer](https://github.com/shimmyshimmer) , **Seems there is a bug when using lora finetune Qwen3, I can't load saved merged model correctly but random init** > > ==((====))== Unsloth 2025.4.1: Fast...
Maybe missing 'glm4.py' in 'unsloth/models' when try to fine-tune. I try to change something in 'qwen2.py' to adapt the 'glm4.py', but failed. So, can unsloth give sone examples to support...