ProCreations Devoloper Team
community
AI & ML interests
AI for the people, not the money.

ProCreations
posted
an
update
14 days ago

ProCreations
posted
an
update
15 days ago

ProCreations
posted
an
update
17 days ago
Post
2368
33 followers AGAIN in another day is insane.... Thank you guys!
trying to get to the #1 trending community article. upvote my article to help out! https://huggingface.co/blog/ProCreations/transformers-are-getting-old
Also, I made a ZeroGPU space that lets you try out smollm3 with no setup needed: Check it out! ProCreations/smollm3
trying to get to the #1 trending community article. upvote my article to help out! https://huggingface.co/blog/ProCreations/transformers-are-getting-old
Also, I made a ZeroGPU space that lets you try out smollm3 with no setup needed: Check it out! ProCreations/smollm3

ProCreations
posted
an
update
18 days ago
Post
2942
20 FOLLOWERS IN LESS THAN A DAY? YA'LL ARE CRAZY!
We zoomed pass 70, 80, and 90 followers in a day. That is insane.
As a thank you, ive published one of my largest and most expensive dataset (rip my 2 dollars, most of my datasets are free to make) to the hub. To be used for text summarization in english, check it out! ProCreations/simple-summaries
We zoomed pass 70, 80, and 90 followers in a day. That is insane.
As a thank you, ive published one of my largest and most expensive dataset (rip my 2 dollars, most of my datasets are free to make) to the hub. To be used for text summarization in english, check it out! ProCreations/simple-summaries

ProCreations
posted
an
update
19 days ago
Post
4772
Transformers are getting old! It’s been 8 whole years since the architecture that powers almost all language models.
Read here for newer alternatives and variants of transformers:
https://huggingface.co/blog/ProCreations/transformers-are-getting-old
Read here for newer alternatives and variants of transformers:
https://huggingface.co/blog/ProCreations/transformers-are-getting-old

ProCreations
posted
an
update
28 days ago
Post
281
ANOTHER new dataset!
Simple facts, about 400 human-sourced facts with no BS.
ProCreations/simple-facts
Also, check out the Simple series!
ProCreations/simple-685f0deec6517268185b37d2
Simple facts, about 400 human-sourced facts with no BS.
ProCreations/simple-facts
Also, check out the Simple series!
ProCreations/simple-685f0deec6517268185b37d2

ProCreations
posted
an
update
30 days ago
Post
295
New dataset I made!
ProCreations/quality-fiction
This is a synthetically made dataset with about 200 examples.
It contains high quality fiction/fantasy story to use for AI training.
ProCreations/quality-fiction
This is a synthetically made dataset with about 200 examples.
It contains high quality fiction/fantasy story to use for AI training.

ProCreations
posted
an
update
about 1 month ago
Post
301
What is AI? Some weird wizards at big companies summoning brains? Humans behind the scenes just responding to requests? Nope. It’s literally JUST math. Some people know this already, but not what actually goes on behind the scenes.
Learn more:
https://huggingface.co/blog/ProCreations/ai-is-nothing-more-than-math
Learn more:
https://huggingface.co/blog/ProCreations/ai-is-nothing-more-than-math

ProCreations
posted
an
update
about 2 months ago

ProCreations
posted
an
update
about 2 months ago
Post
1073
NEW DATASETTTTT
ProCreations/Ultra-FineWeb-EDU
This dataset is an extremely filtered version of
openbmb/Ultra-FineWeb
for educational content only, inspired by
HuggingFaceFW/fineweb-edu
Right now dataset size is small (64k examples) and more examples are being processed as you read this!
ProCreations/Ultra-FineWeb-EDU
This dataset is an extremely filtered version of
openbmb/Ultra-FineWeb
for educational content only, inspired by
HuggingFaceFW/fineweb-edu
Right now dataset size is small (64k examples) and more examples are being processed as you read this!

ProCreations
posted
an
update
about 2 months ago
Post
205
here’s a bunch of mcp’s I made for Claude because I was bored
https://github.com/ProCreations-Official/HuggingMCP
https://github.com/ProCreations-Official/gitmcp
https://github.com/ProCreations-Official/second-opinion
https://github.com/ProCreations-Official/HuggingMCP
https://github.com/ProCreations-Official/gitmcp
https://github.com/ProCreations-Official/second-opinion

ProCreations
posted
an
update
about 2 months ago

ProCreations
posted
an
update
about 2 months ago
Post
291
Introducing my custom AI lab!
This huggingface shows a bunch of fundamental visuals of AI’s training in real time.
ProCreations/ai-labs
Updates coming soon with a walk through mode that teaches you what it all means!
Meanwhile if you want to learn about AI and not just see it,
ProCreations/learn-ai
This huggingface shows a bunch of fundamental visuals of AI’s training in real time.
ProCreations/ai-labs
Updates coming soon with a walk through mode that teaches you what it all means!
Meanwhile if you want to learn about AI and not just see it,
ProCreations/learn-ai

ProCreations
posted
an
update
2 months ago

ProCreations
posted
an
update
2 months ago
Post
2427
Uggghhh what a busy week.
Been up all night fixing Intellite and I got some progress I wanted to share.
ALL errors we experienced (there’s a lot):
Gradient vanishing (AI dies)
Gradient explosion (AI barely learns and destabilizes)
Activation Explosion (AI dies)
Layer Scale Crushing Signal (AI dies)
Activation Explosion (again) (AI dies)
All fixed, but now it keeps overfitting on datasets due to a dataset handler error 😩
Been up all night fixing Intellite and I got some progress I wanted to share.
ALL errors we experienced (there’s a lot):
Gradient vanishing (AI dies)
Gradient explosion (AI barely learns and destabilizes)
Activation Explosion (AI dies)
Layer Scale Crushing Signal (AI dies)
Activation Explosion (again) (AI dies)
All fixed, but now it keeps overfitting on datasets due to a dataset handler error 😩

ProCreations
posted
an
update
2 months ago
Post
524
PROGRESS REPORT
Intellite Chat is going well! I have made format much more uniform (now chatml), data handling now works, and we removed and added new datasets for a better mix of quality. I have also updated the default model to be fp16 instead of fp32 for faster training. Stay tuned!
Intellite Chat is going well! I have made format much more uniform (now chatml), data handling now works, and we removed and added new datasets for a better mix of quality. I have also updated the default model to be fp16 instead of fp32 for faster training. Stay tuned!

ProCreations
posted
an
update
2 months ago
Post
3187
Eyyy thank you guys for 40 followers!

ProCreations
posted
an
update
2 months ago
Post
455
Question about Intellite Chat to you guys!
(If you don’t know, Intellite Chat is my up-and-coming 100m parameter AI model focused on high-quality chat.)
What quantization variants would you want to see for Intellite Chat? It’ll come with FP32, FP16, and BF16, but any others you want? Maybe FP8 or even BitNet’s 1.58-bit quantization? Let me know!
(If you don’t know, Intellite Chat is my up-and-coming 100m parameter AI model focused on high-quality chat.)
What quantization variants would you want to see for Intellite Chat? It’ll come with FP32, FP16, and BF16, but any others you want? Maybe FP8 or even BitNet’s 1.58-bit quantization? Let me know!

ProCreations
posted
an
update
2 months ago
Post
1907
I made a space!
Check out
https://huggingface.co/spaces/ProCreations/realtime-ai-visualization
This cool space visualizes a real neural net in real time. It trains a real 199 parameter model on XOR. With baby mode for non-devs and advanced mode for developers or enthusiasts, (hopefully) everyone will understand!
Check out
https://huggingface.co/spaces/ProCreations/realtime-ai-visualization
This cool space visualizes a real neural net in real time. It trains a real 199 parameter model on XOR. With baby mode for non-devs and advanced mode for developers or enthusiasts, (hopefully) everyone will understand!

ProCreations
posted
an
update
2 months ago
Post
1178
My first ever working model!
Introducing tinyvvision. An extremely small zero shot image classification model for simple shapes, letters, colors, and numbers. This is a foundation model for Intellision, an image-text-to-text model, which will be much bigger but still impressively small.
ProCreations/tinyvvision
NOTE: it’s small, mistakes will happen!!!! Not meant for complex stuff, just a demo for simple stuff.
Introducing tinyvvision. An extremely small zero shot image classification model for simple shapes, letters, colors, and numbers. This is a foundation model for Intellision, an image-text-to-text model, which will be much bigger but still impressively small.
ProCreations/tinyvvision
NOTE: it’s small, mistakes will happen!!!! Not meant for complex stuff, just a demo for simple stuff.