hanwenxu1

[Usage] Error when use cli.py after merge-lora-weights.py

1

### Describe the issue Issue: I used finetune_lora.sh to finetune vicuna-v1.5-13b with custom data. After it, I got a folder with adapter_model.safetensors, non_lora_trainables.bin. Then I merged it by merge-lora-weights.py, and...

I'm trying to use `train_cogvideox_lora.py` to finetune 2b model with customized dataset. When I set the train lr is 1e-5, and the epoch is 2, I get some normal result....

which is the feishu api key?

5

When I use Feishu's send message function, I always encounter an 'Invalid access token for authorization' error. I'm not sure which Feishu API key should be entered on the aci.dev...

About BCEloss with abnormal score

1

I have know that we can calculate the abnormal scores by the number of abnormal blocks. But I notice that a sigmoid layer and binary cross-entropy been used in the...