-
We are currently using the Whisper-Tiny multilingual model and seeking ways to improve its performance. We would appreciate any insights or suggestions on how to enhance the model's accuracy, speed, a…
-
Training process always stops / freezes at epoch1 - cannot train - anybody an idea ? Please help.
here is the Protocol:
To create a public link, set `share=True` in `launch()`.
15:58:52-915530…
-
I tried to train with clip_L vision encoder, (by adding vit_model: "clip_L" to model train config), but it seems the QFormer checkpoint loaded by default at this line (https://github.com/salesforce/LA…
-
Error occurred when executing NEW_PhotoMaker_Generation:
"LayerNormKernelImpl" not implemented for 'Half'
File "D:\Ai\SD-N\ComfyUI\execution.py", line 155, in recursive_execute
output_data, out…
-
Trying to experiment with perceptual model, upon training it says:
```
Traceback (most recent call last):
File "train.py", line 490, in
main_function(config)
File "train.py", line 224,…
-
loss often increase suddenly and led to the model's failure to converge. Have you ever encountered this situation? Have you alleviated it by setting `grad clip` and other parameters?
-
Hi, thanks for this amazing library.
I saw one tiny issue which is that the final weights of the model is different when training with multiple sub_batches per step vs 1 big_batch per step. I'm not…
-
Hi,
I want to fine-tune the CLIP model with my dataset. The size of the dataset is very large. There are more than 2M image-text pairs. I tried various learning rates including too-small learning rat…
-
When I run pretrain scripts,
I got this:
File "/data/lc/Multi-image/multi_token/multi_token/language_models/mistral.py", line 85, in forward
) = self.prepare_inputs_labels_for_multimodal(
F…
-
Thanks for your nice work!
I have a question, If I replace the decoder with the SD series, will it affect the final generation performance?