DavidVivancos/NeuraxonLife2-1M
Updated
β’
1
John Smith PRO
John6666
AI & ML interests
None yet
Recent Activity
liked
a dataset
about 2 hours ago
DavidVivancos/NeuraxonLife2-1M
reacted
to
DavidVivancos's
post
with π
about 2 hours ago
Need a new challenging Dataset? Now that #NeurIPS2025 is almost over.
https://huggingface.co/datasets/DavidVivancos/NeuraxonLife2-1M
1 Million #Neuraxon Artificial Lives, from almost 10000 Research Game runs, with more than 21 Million Neurons and almost 4 years of Simulated Life.
Read the preprint here https://www.researchgate.net/publication/397331336_Neuraxon
And here you have all the code: https://github.com/DavidVivancos/Neuraxon
reacted
to
omarkamali's
post
with π
about 2 hours ago
Hello `picomon`! AMD GPU Monitoring made easy
Just run `uvx picomon` and behold:
```
ββββββββββββββββββββββββββββββββββββββββββββ ββββββββββββββββββββββββββββββββββββββββββββ
β GPU 0 GFX 42% UMC 21% β β GPU 1 GFX 78% UMC 66% β
β PWR 135/250W (54%) VRAM 10.0/16.0GB 62% β β PWR 210/250W (84%) VRAM 14.5/16.0GB 90% β
β β β β
β GFX βββββββ
βββββββ
ββββ β β GFX ββββ
βββββββ
βββββ
β β
β PWR ββββββββ
βββββββ
βββ β β PWR βββββ
βββββββ
βββββ β
β VRM ββββββββ
ββββββββ
ββ β β VRM ββββ
βββββββββ
ββββ β
ββββββββββββββββββββββββββββββββββββββββββββ ββββββββββββββββββββββββββββββββββββββββββββ
```
Repo at https://github.com/omarkamali/picomon
Or pypi at https://pypi.org/project/picomon
Organizations
liked
a
dataset
about 2 hours ago
reacted to
DavidVivancos's
post with π
about 2 hours ago
Post
76
Need a new challenging Dataset? Now that #NeurIPS2025 is almost over.
DavidVivancos/NeuraxonLife2-1M
1 Million #Neuraxon Artificial Lives, from almost 10000 Research Game runs, with more than 21 Million Neurons and almost 4 years of Simulated Life.
Read the preprint here https://www.researchgate.net/publication/397331336_Neuraxon
And here you have all the code: https://github.com/DavidVivancos/Neuraxon
DavidVivancos/NeuraxonLife2-1M
1 Million #Neuraxon Artificial Lives, from almost 10000 Research Game runs, with more than 21 Million Neurons and almost 4 years of Simulated Life.
Read the preprint here https://www.researchgate.net/publication/397331336_Neuraxon
And here you have all the code: https://github.com/DavidVivancos/Neuraxon
reacted to
omarkamali's
post with π
about 2 hours ago
Post
186
Hello
Just run
Repo at https://github.com/omarkamali/picomon
Or pypi at https://pypi.org/project/picomon
picomon! AMD GPU Monitoring made easyJust run
uvx picomon and behold:ββββββββββββββββββββββββββββββββββββββββββββ ββββββββββββββββββββββββββββββββββββββββββββ
β GPU 0 GFX 42% UMC 21% β β GPU 1 GFX 78% UMC 66% β
β PWR 135/250W (54%) VRAM 10.0/16.0GB 62% β β PWR 210/250W (84%) VRAM 14.5/16.0GB 90% β
β β β β
β GFX βββββββ
βββββββ
ββββ β β GFX ββββ
βββββββ
βββββ
β β
β PWR ββββββββ
βββββββ
βββ β β PWR βββββ
βββββββ
βββββ β
β VRM ββββββββ
ββββββββ
ββ β β VRM ββββ
βββββββββ
ββββ β
ββββββββββββββββββββββββββββββββββββββββββββ ββββββββββββββββββββββββββββββββββββββββββββRepo at https://github.com/omarkamali/picomon
Or pypi at https://pypi.org/project/picomon
reacted to
Teen-Different's
post with π
about 2 hours ago
Post
65
STRAW: Sample-Tuned Rank-Augmented Weights
Dropped a write-up on a weird direction Iβve been exploring lately.
Itβs basically a lightweight, low-rank hypernetwork that rewrites a modelβs weights per sample instead of running everything through a frozen graph. Iβm calling it STRAW (Sample-Tuned Rank-Augmented Weights), a tiny modulator that generates dynamic LoRA-style updates on the fly, so the model morphs its own parameters based on the inputβs βvibe.β
The good part is it actually trains stably and outperforms a static baseline in low-data regimes. Not SOTA (obviously), but the fact that real-time weight modulation didnβt collapse was the whole point. Next step is making the modulator actually understand geometry instead of just reacting to pixels.
This is still early more βresearch logβ than polished result but it opens up a fun direction toward liquid-ish, context-shaped networks instead of rigid ones.
Blog: https://teendifferent.substack.com/p/sample-tuned-rank-augmented-weights
Dropped a write-up on a weird direction Iβve been exploring lately.
Itβs basically a lightweight, low-rank hypernetwork that rewrites a modelβs weights per sample instead of running everything through a frozen graph. Iβm calling it STRAW (Sample-Tuned Rank-Augmented Weights), a tiny modulator that generates dynamic LoRA-style updates on the fly, so the model morphs its own parameters based on the inputβs βvibe.β
The good part is it actually trains stably and outperforms a static baseline in low-data regimes. Not SOTA (obviously), but the fact that real-time weight modulation didnβt collapse was the whole point. Next step is making the modulator actually understand geometry instead of just reacting to pixels.
This is still early more βresearch logβ than polished result but it opens up a fun direction toward liquid-ish, context-shaped networks instead of rigid ones.
Blog: https://teendifferent.substack.com/p/sample-tuned-rank-augmented-weights
reacted to
onekq's
post with π
about 2 hours ago
Post
66
I am starting a new series on matrix. The idea came to me when I wrote about the Muon optimizer.
Matrix itself has lots of fascinating properties and is applied in STEM fields for many decades. Its application in ML is just the beginning. There are lots of low hanging fruits. At the very least, I hope this math perspective will give you a new lens.
https://huggingface.co/blog/onekq/matrices-transformers-preface
Matrix itself has lots of fascinating properties and is applied in STEM fields for many decades. Its application in ML is just the beginning. There are lots of low hanging fruits. At the very least, I hope this math perspective will give you a new lens.
https://huggingface.co/blog/onekq/matrices-transformers-preface
- 2 replies
reacted to
ovi054's
post with π₯
about 2 hours ago
Post
233
Anim Lab AIβ‘
Turn any math concept or logic into a clear video explanation instantly using AI.
This is my submission for the MCP 1st Birthday Hackathon, and itβs already crossed 1,000 runs.
π Try it now: MCP-1st-Birthday/anim-lab-ai
Demo outputs are attached π
Turn any math concept or logic into a clear video explanation instantly using AI.
This is my submission for the MCP 1st Birthday Hackathon, and itβs already crossed 1,000 runs.
π Try it now: MCP-1st-Birthday/anim-lab-ai
Demo outputs are attached π
reacted to
kanaria007's
post with π
about 2 hours ago
Post
87
β
New Article: *Measuring Structured Intelligence*
Title:
π Measuring Structured Intelligence in Practice
π https://huggingface.co/blog/kanaria007/measuring-structured-intelligence
---
Summary:
βIntelligentβ, βalignedβ, βresilientβ β we use these words a lot, but what do they *numerically* mean?
This article turns Structured Intelligence from a philosophy into something you can *monitor, compare, and debug*.
It pulls together metrics like *CAS, SCI, SCover, EAI, RBL, RIR* and friends into a coherent evaluation layer for SI-Core, SIC, and AGI-adjacent systems.
> If you canβt measure how structure behaves under stress,
> *you canβt claim itβs intelligent β only hopeful.*
---
Why It Matters:
β’ Moves beyond leaderboard benchmarks to *system-level behavior metrics*
β’ Lets you track *causality alignment, rollback safety, ethics gating, and coverage* as first-class signals
β’ Provides a common language for *researchers, infra teams, and policy folks* to talk about βhow alignedβ a system really is
β’ Bridges day-to-day engineering KPIs with *cosmic-scale metrics* introduced in the broader Structured Intelligence work
---
Whatβs Inside:
β’ A clean overview of core metrics (e.g. CAS, SCI, SCover, EAI, RBL, RIR) and what they *actually* tell you
β’ How to instrument SI-Core / SIC stacks so these numbers fall out of normal operation
β’ Examples: βgoodβ vs βbadβ metric profiles for agents, rollbacks, effectful tools, and governance loops
β’ How micro-level metrics roll up into *macro and cosmic indicators* (e.g. structural resilience, long-horizon stability)
β’ Practical notes on logging, sampling, and avoiding KPI theater
---
π Structured Intelligence Engineering Series
This piece is the metrics counterpart to the architectural articles β
turning Structured Intelligence from βjust very coherentβ into something you can *graph, alert on, and iterate*.
Title:
π Measuring Structured Intelligence in Practice
π https://huggingface.co/blog/kanaria007/measuring-structured-intelligence
---
Summary:
βIntelligentβ, βalignedβ, βresilientβ β we use these words a lot, but what do they *numerically* mean?
This article turns Structured Intelligence from a philosophy into something you can *monitor, compare, and debug*.
It pulls together metrics like *CAS, SCI, SCover, EAI, RBL, RIR* and friends into a coherent evaluation layer for SI-Core, SIC, and AGI-adjacent systems.
> If you canβt measure how structure behaves under stress,
> *you canβt claim itβs intelligent β only hopeful.*
---
Why It Matters:
β’ Moves beyond leaderboard benchmarks to *system-level behavior metrics*
β’ Lets you track *causality alignment, rollback safety, ethics gating, and coverage* as first-class signals
β’ Provides a common language for *researchers, infra teams, and policy folks* to talk about βhow alignedβ a system really is
β’ Bridges day-to-day engineering KPIs with *cosmic-scale metrics* introduced in the broader Structured Intelligence work
---
Whatβs Inside:
β’ A clean overview of core metrics (e.g. CAS, SCI, SCover, EAI, RBL, RIR) and what they *actually* tell you
β’ How to instrument SI-Core / SIC stacks so these numbers fall out of normal operation
β’ Examples: βgoodβ vs βbadβ metric profiles for agents, rollbacks, effectful tools, and governance loops
β’ How micro-level metrics roll up into *macro and cosmic indicators* (e.g. structural resilience, long-horizon stability)
β’ Practical notes on logging, sampling, and avoiding KPI theater
---
π Structured Intelligence Engineering Series
This piece is the metrics counterpart to the architectural articles β
turning Structured Intelligence from βjust very coherentβ into something you can *graph, alert on, and iterate*.
upvoted
an
article
about 2 hours ago
Article
Ellora: Enhancing LLMs with LoRA - Standardized Recipes for Capability Enhancement
β’
10
reacted to
codelion's
post with π₯
about 2 hours ago
Post
222
NotebookLM's infographics feature is amazing, it generates poster-type images from any text. Here is one I tried for my new HF article on ellora - https://huggingface.co/blog/codelion/ellora-lora-recipes
reacted to
ZennyKenny's
post with π
about 2 hours ago
Post
81
What a trip. Just walked through
@burtenshaw
and
@evalstate
tutorial on adding Hugging Face Skills to your Claude Code agent so you can fine tune LLMs by chatting with AI.
These are the kinds of innovations that are going to help everyone benefit from the power of Artificial Intelligence. Well done gentlemen and thank you for sharing.
These are the kinds of innovations that are going to help everyone benefit from the power of Artificial Intelligence. Well done gentlemen and thank you for sharing.
- 1 reply
updated
a
dataset
about 2 hours ago
liked
9
models
about 3 hours ago
huihui-ai/Huihui-Ministral-3-8B-Reasoning-2512-abliterated
9B
β’
Updated
β’
40
β’
4
mradermacher/Huihui-Ministral-3-8B-Reasoning-2512-abliterated-i1-GGUF
8B
β’
Updated
β’
3.24k
β’
1
mradermacher/Huihui-Ministral-3-8B-Reasoning-2512-abliterated-GGUF
8B
β’
Updated
β’
863
β’
1
Yuma42/Llama3.1-DeluXeOne-8B
8B
β’
Updated
β’
24
β’
1
mradermacher/Llama3.1-DeluXeOne-8B-GGUF
8B
β’
Updated
β’
567
β’
1
mradermacher/Llama3.1-DeluXeOne-8B-i1-GGUF
8B
β’
Updated
β’
4.51k
β’
1
WokeAI/Tankie-DPE-12b-SFT
Text Generation
β’
12B
β’
Updated
β’
41
β’
3
mradermacher/Tankie-DPE-12b-SFT-GGUF
12B
β’
Updated
β’
728
β’
1
mradermacher/Tankie-DPE-12b-SFT-i1-GGUF
12B
β’
Updated
β’
4.95k
β’
1