-
Hi, thanks for open sourcing this awesome work. Your work builds an interesting connection between consistency distillation and score distillation from the view of cross-consistency. When I tried to u…
-
SiD is a very good work, Thank you very much!
We notice you team new work: ADVERSARIAL SCORE IDENTITY DISTILLATION: RAPIDLY SURPASSING THE TEACHER IN ONE STEP, did SiDA code open source?
-
We aim to implement a system that leverages distillation and quantization to create a "child" neural network by combining parameters from two "parent" neural networks. The child network should inherit…
-
I assume launch_inference.sh is meant to run inference on the motorcycle image. But so far it's been going for over 30 mins with no end in sight. I also noticed it calls launch.py in `--train` mode. I…
-
Hello,
should I expect a high f1 score when training only the first step (intermediate-layers) distillation on SQuAD1.1?
Thanks
-
The HPLT dataset includes a fluency score. We should look at filtering our own data by this fluency metric, and see if it improves.
https://hplt-project.org/datasets/v1.2
I assume this would be …
-
Right now, for simplicity, during distillation we pad every document to the max length so we can easily stack them to compute the scores.
An optimization would be to only pad them to the longest in t…
-
Hi, thanks for your wonderful work~
I'm a little confused about the implemention of vsd loss,
I followed your paper and read _ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with V…
-
In #771 I ran an experiment to see the effects of the size of the distillation corpus for the change in the COMET score for the students. Adding more data to this step did not affect the COMET score b…
-
I attempted to run Lloom on a sample corpus consisting of news articles (I am running on python 3.9 and downgraded the openAI version as stated in the instructions).
When I first tried to run, I r…