bingoHong

wgan loss is right?

2

https://github.com/wiseodd/generative-models/blob/c790d2c8add3d600c03ee9a301a969e10ccd7562/GAN/wasserstein_gan/wgan_tensorflow.py#L82-L83 in the code , you define the discriminator loss is : `D_loss = tf.reduce_mean(D_real) - tf.reduce_mean(D_fake) ` however the generator loss is: `G_loss = - tf.reduce_mean(D_fake) ` i think...

I complete the SN by Keras. welcome to advice

2

location in [SN by Keras](https://github.com/Bingohong/SwitchableNormalization-Keras)

Musedataset cannot download

12

urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='docs.google.com', port=443): Max retries exceeded with url: /uc?export=download&id=1a5361IfxxEY1mmTfqAviiIkq6u2OYFJ7 (Caused by NewConnectionError(': Failed to establish a new connection: [Errno 111] Connection refused',)) ------------------------------------------------------- I can't get musedata from docs.google.com by...

llama-13b-hf做推理，CUDA out of memory. 问题

2

我这里尝试使用llama-13b-hf做推理，设备是4张10G 3080，上游模型应该就18G，但在加载lora模型时，就会报下列错误。 `log torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 26.00 MiB (GPU 0; 10.00 GiB total capacity; 8.82 GiB already allocated; 0 bytes free; 8.82 GiB reserved in...