4 1 13

Brad

Firepal3D

AI & ML interests

None yet

Recent Activity

new activity about 22 hours ago

NousResearch/k2-merged-3.5T-fp8:Is this even runnable?

liked a model 3 days ago

TheDrummer/Rivermind-12B-v1

liked a model 17 days ago

allura-org/Gemma-3-Glitter-12B

View all activity

Organizations

None yet

New activity in NousResearch/k2-merged-3.5T-fp8 about 22 hours ago

Is this even runnable?

#1 opened about 22 hours ago by

Firepal3D

liked a model 3 days ago

TheDrummer/Rivermind-12B-v1

12B • Updated Oct 31, 2025 • 26 • 43

liked a model 17 days ago

allura-org/Gemma-3-Glitter-12B

Any-to-Any • 12B • Updated Mar 28, 2025 • 48 • 26

liked 4 models 20 days ago

reacted to inflatebot's post with 🔥 3 months ago

Post

1551

Pressure from far-right activist groups is inducing payment processors to crack down on adult content on mainstream platforms (where previously they were restricted in scope to adult platforms), starting first with Steam, now recently itch.io. We saw similar on Civit recently, except they were unlucky enough to have partnered with a payment processor who didn't care that they complied and pulled out anyway. A friend of mine recently lost all her income because of similar stuff (and the Itch move badly hurt other people in my circles.)

This is pretty far-removed from a lot of the people reading this, andI don't want to tell you how to feel about this happening, *but all the same, don't assume that Hugging Face is going to be safe because it's an "academic-coded" platform.* If you make things for mature audiences here, please make sure you have local backups of your data and models.

That's all I got. Be safe out there.

New activity in Mungert/rwkv7-2.9B-g1-GGUF 3 months ago

broken chat template?

#1 opened 4 months ago by

Firepal3D

reacted to grimjim's post with 🔥 9 months ago

Post

2361

I recently have been looking at a paper titled "Why Warmup the Learning Rate? Underlying Mechanisms and Improvements", by Dayal Singh Kalra and Maissam Barkeshli, and was struck by "warmup" being analogous to simulated annealing.
https://arxiv.org/abs/2406.09405
Taking the physical analogy further, the "warmup" is a stochastic process to knock the system out of current local minima, allowing easier transition toward newer minima. It works because it reduces "fit" and therefore "friction".

upvoted an article 9 months ago

Article

Comparing sub 50GB Llama 4 Scout quants (KLD/Top P)

Apr 9, 2025

•

liked a dataset 10 months ago

inclinedadarsh/nl-to-regex

Viewer • Updated Mar 24, 2025 • 824 • 34 • 2

New activity in Qwen/Qwen2.5-0.5B about 1 year ago

VRAM Requirements

#2 opened about 1 year ago by

ahmaddanyal

reacted to bartowski's post with ❤️ about 1 year ago

Post

23969

In regards to the latest mistral model and GGUFs for it:

Yes, they may be subpar and may require changes to llama.cpp to support the interleaved sliding window

Yes, I got excited when a conversion worked and released them ASAP

That said, generation seems to work right now and seems to mimic the output from spaces that are running the original model

I have appended -TEST to the model names in an attempt to indicate that they are not final or perfect, but if people still feel mislead and that it's not the right thing to do, please post (civilly) below your thoughts, I will highly consider pulling the conversions if that's what people think is best. After all, that's what I'm here for, in service to you all !