Stable Diffusion 3.5 Large
🏃
Generate images with SD3.5
Hector Henriquez PRO
SeedOfEvil
·
AI & ML interests
Real-world AI Applications & Integrations, Generative AI & Large Language Models, AI in Gaming & Interactive Experiences.
Recent Activity
updated
a Space
3 days ago
SeedOfEvil/stable-diffusion-3.5-large-SoE
updated
a Space
3 days ago
SeedOfEvil/stable-diffusion-3.5-large-turboX-SoE
published
a Space
3 days ago
SeedOfEvil/stable-diffusion-3.5-large-turboX-SoE
Organizations
None yet
SeedOfEvil's activity
updated
2
Spaces
3 days ago
published
a
Space
3 days ago
liked
2
models
3 days ago
updated
a
Space
3 days ago
published
2
Spaces
4 days ago
liked
a
model
4 days ago
reacted to
clefourrier's
post with 👍
4 days ago
Post
1601
Gemma3 family is out! Reading the tech report, and this section was really interesting to me from a methods/scientific fairness pov.
Instead of doing over-hyped comparisons, they clearly state that **results are reported in a setup which is advantageous to their models**.
(Which everybody does, but people usually don't say)
For a tech report, it makes a lot of sense to report model performance when used optimally!
On leaderboards on the other hand, comparison will be apples to apples, but in a potentially unoptimal way for a given model family (like some user interact sub-optimally with models)
Also contains a cool section (6) on training data memorization rate too! Important to see if your model will output the training data it has seen as such: always an issue for privacy/copyright/... but also very much for evaluation!
Because if your model knows its evals by heart, you're not testing for generalization.
Instead of doing over-hyped comparisons, they clearly state that **results are reported in a setup which is advantageous to their models**.
(Which everybody does, but people usually don't say)
For a tech report, it makes a lot of sense to report model performance when used optimally!
On leaderboards on the other hand, comparison will be apples to apples, but in a potentially unoptimal way for a given model family (like some user interact sub-optimally with models)
Also contains a cool section (6) on training data memorization rate too! Important to see if your model will output the training data it has seen as such: always an issue for privacy/copyright/... but also very much for evaluation!
Because if your model knows its evals by heart, you're not testing for generalization.
liked
a
Space
4 days ago
liked
a
Space
5 days ago
updated
a
Space
5 days ago
Tested working 5 second took 3 minutes on L40S setup
#1 opened 5 days ago
by
SeedOfEvil
published
a
Space
5 days ago
updated
2
Spaces
5 days ago