hl
3是指三个 特殊符号 start end unk 太久了 不太记得
@wutaiqiang so， how to implement residual connection， when inputs feature dimension[*, 1433] not equal to self.gc1() output size [*, 16] ?
I have been facing the same issue
transformers 4.49.0 transformers-stream-generator 0.0.5 accelerate 1.4.0 deepspeed 0.15.0 torch 2.6.0 torchaudio 2.6.0 torchinfo 1.8.0 torchmetrics 1.6.1 torchvision 0.21.0 Hello @SunMarc I use this repo https://github.com/s-JoL/Open-Llama train llm model, save model...
@yy12315 抱歉啊，分割的模型在这个https://github.com/CSAILVision/semantic-segmentation-pytorch 工程里面，可以看看它提供的模型链接