-
I wanted to report a small bug I found when going a bit deeper into the code.
In `trainer.py` there is a function for computing the unit norm of the training data. This is the function:
def …
-
Like number of binning: 20 or 30, missing value processing type, these should impact model performance in triaining,
how to add such parameters to grid search?
-
@SoongNoonien has some concern that this may be too slow if we do it for all. So this raises a few new questions
- how long does it take to just *load* all tables?
- how long does it take to compute…
-
```bash
[vite:css] Failed to find '@/norm.css'
in [
/Users/weiran/repo/dian/vite-tsconfig-paths/demo/src
]
file: /Users/weiran/repo/dian/vite-tsconfig-paths/demo/src/styles.css
error dur…
-
Hi! Following up on question #6 .
I can see that this project uses the [cn_tn.py](https://github.com/speechio/chinese_text_normalization/blob/master/python/cn_tn.py)-file which specifies these auth…
faaip updated
2 months ago
-
It makes sense that "embed_tokens" should be specified in "modules_to_save" since that is not a linear layer.
But, lm_head is a linear layer - so why not allow LoRA to be applied there?
Also, wh…
-
It would be nice to have a toggle between log and linear norm for `LiveImage`.
## Expected Behavior
Press button and plot changes scale
## Current Behavior
Scale must be set at instantiation
…
-
-
Dear Team, Thank you for the great work.
I was currently exploring the InternVideo2-Chat 8B and had a few questions/doubts regarding it.
1. What is the visual encoder used? Is it the InternVideo2 …
-
via Email:
> der KS-Test wie auch die uniform-ecdf-Methode eher unterpowert sind, d.h., man geht zu spät von Abweichungen im Modell aus. Da ich auch heute noch häufig lineare mixed models (also LMM…