Robert Sinclair

ZeroWw

AI & ML interests

LLMs optimization (model quantization and back-end optimizations) so that LLMs can run on computers of people with both kidneys. Discord: https://discord.com/channels/@robert_46007

Recent Activity

liked a model 17 days ago

inflatebot/MN-12B-Mag-Mell-R1

liked a model 17 days ago

inflatebot/MN-12B-Mag-Mell-R1-GGUF

new activity 17 days ago

inflatebot/MN-12B-Mag-Mell-R1:Great model! Smaller perhaps?

View all activity

Organizations

ZeroWw's activity

liked 2 models 17 days ago

inflatebot/MN-12B-Mag-Mell-R1

Text Generation • Updated 3 days ago • 1.55k • 73

inflatebot/MN-12B-Mag-Mell-R1-GGUF

Updated Sep 16 • 5.33k • 9

New activity in inflatebot/MN-12B-Mag-Mell-R1 17 days ago

Great model! Smaller perhaps?

#10 opened 17 days ago by

ZeroWw

New activity in ggerganov/whisper.cpp 18 days ago

Please add the medium-it model

#22 opened 18 days ago by

ZeroWw

New activity in deepseek-ai/DeepSeek-V2 20 days ago

This is by far the best model I have seen until now.

#8 opened 6 months ago by

ZeroWw

updated 2 models 25 days ago

ZeroWw/Marco-o1-SILLY

Text Generation • Updated 25 days ago • 35

ZeroWw/Marco-o1-GGUF

Text Generation • Updated 25 days ago • 116

New activity in DavidAU/L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-GGUF about 2 months ago

Brainstorm 40x method developed by David_AU

#1 opened about 2 months ago by

ZeroWw

Silly version

#2 opened about 2 months ago by

ZeroWw

updated a model about 2 months ago

ZeroWw/L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-D_AU-SILLY

Text Generation • Updated Oct 29 • 9 • 1

replied to TuringsSolutions's post about 2 months ago

hence my idea of the SILLY versions... ;)

replied to TuringsSolutions's post about 2 months ago

I am pretty sure that the actual models "AS THEY ARE" could perform 10 times better using chain of thought and some algorithms like these. Without needing a different training. And I think that's probably what CLAUDE does,

reacted to TuringsSolutions's post with ❤️ about 2 months ago

Post

2105

Transformers are not all we need, that is being proven repeatedly now as more alternative frameworks emerge. Another such framework is Kolmogorov Arnold Network based Transformers. I break down exactly how these differ from Perceptron based Transformers and give you the link to my Colab where I create a model based on the research paper that absolutely destroys a standard Transformers based model. Check out the video here: https://www.youtube.com/watch?v=Sw0euxNZCc4

reacted to TuringsSolutions's post with ❤️ about 2 months ago

Post

1411

I think Reinforcement Learning is the future, for a lot of reasons. I spell them out for you in this video, and also provide you with the basic code to get up and running with Atari and OpenAI Gym. If you want to get into RL, this is your ticket. Link to a cool training montage of the model in the description of the video as well. Step 2 from here would be the full-on training and certification that HuggingFace offers for RL.

https://youtu.be/ueZl3A36ZQk