lyricpoem
lyricpoem
不管是群里面还是个人都无法收到回复,却显示了消息发送成功
Thank you for your repo. I have a question about the way of word embedding in these captioning models. Why word embedding layer is followed by a ReLU layer? Since...
Two days ago, I train a Dit-XL with the following command: ``` torchrun --nproc_per_node=8 src/train.py \ --model DiT-XL/122 \ --vae ucf101_stride4x4x4 \ --data-path ./UCF-101 --num-classes 101 \ --sample-rate 2 --num-frames...
Thank you for your idea and repo. Since box embedding and w_g stay same in multi-turn multihead attention and they do not rely on k,q,v. Is it proper to move...
LLama-factory的训练文档有处不一致,原始文档中,构建sharegpt格式数据时,文档给出的示例是: `dataset.json` ``` [ { "conversations": [ { "from": "human", "value": "user instruction" }, { "from": "gpt", "value": "model response" } ], "system": "system prompt (optional)", "tools": "tool description (optional)"...