Update README.md
Browse files
README.md
CHANGED
|
@@ -10,6 +10,13 @@ This isn't a bad first test. I will be improving the adapter with common lora te
|
|
| 10 |
|
| 11 |
Given time I'm certain this will work; whether it be creating a layered lora structure to interpolate differences layer by layer within the clip_l, or perhaps in a much more direct neuron interpolation. Time will tell and I'm definitely enjoying this sort of thing.
|
| 12 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
|
| 14 |
```
|
| 15 |
def main():
|
|
|
|
| 10 |
|
| 11 |
Given time I'm certain this will work; whether it be creating a layered lora structure to interpolate differences layer by layer within the clip_l, or perhaps in a much more direct neuron interpolation. Time will tell and I'm definitely enjoying this sort of thing.
|
| 12 |
|
| 13 |
+
Errors to address in the next;
|
| 14 |
+
* There is a clamping index error that tends to rear it's head that I haven't had time to track down. It'll cause solid black images from the velocity sigmas being too heavy.
|
| 15 |
+
* Occasionally the entire structure of a generation collapses, which means the sigmas aren't lined up correctly - creating malformed sigma responses.
|
| 16 |
+
* Occasionally the substructure interprets the request incorrectly; this is due to the tokenization being inaccurately attuned for some spaces than others and this next version will have node weighting for specific attention head sectors to account for it.
|
| 17 |
+
|
| 18 |
+
There's many challenges ahead to reach the interpolation endpoint but it's definitely an adaptive journey.
|
| 19 |
+
|
| 20 |
|
| 21 |
```
|
| 22 |
def main():
|