ποΈ Building on HF
AxionLab
AxionLab-official
AI & ML interests
Owner of SupraLabs
Recent Activity
new activity 1 day ago
AtomixLabs/blog:lol new activity 1 day ago
AtomixLabs/blog:son reacted to DedeProGames's post with π₯ 1 day ago
We are working on LFM3-1.7B-Ox, a compact model for repo-level programming, agentic coding, and tinkering.Organizations
reacted to DedeProGames's post with π₯ 1 day ago
This comment has been hidden
reacted to appvoid's post with β€οΈ 11 days ago
Post
7,609
New leaderboard coming to the small language model community!
The leaderboard measures cognitive skills, which is more challenging and beyond language modeling and instruction-following. This is a first step towards more everyday useful and general small models.
dotlabs/cognirank
The leaderboard measures cognitive skills, which is more challenging and beyond language modeling and instruction-following. This is a first step towards more everyday useful and general small models.
dotlabs/cognirank
reacted to Banaxi-Tech's post with π 20 days ago
reacted to Banaxi-Tech's post with π 22 days ago
reacted to appvoid's post with π₯ 22 days ago
Post
4,014
You know, I can't believe we are actually doing it, literally advancing the frontier at the edge! We've come a long way since the first models on open slm leaderboard, and, as many things that change, performance is one of the main things that has exploded.
7 years ago, the best we had was GPT-2. Today, we got 90m models beating smollm2! I can't barely see what a future with increasingly powerful small models will look like.
All I can say is that the best is yet to come. And will be agentic.
7 years ago, the best we had was GPT-2. Today, we got 90m models beating smollm2! I can't barely see what a future with increasingly powerful small models will look like.
All I can say is that the best is yet to come. And will be agentic.
reacted to DedeProGames's post with π§ ππ₯ about 1 month ago
Post
3,468
Meet Supra2.5-Ultra-Preview-001. 230M parameters, ~40.4B training tokens.
SupraLabs has released the first preview of its Supra2.5-Ultra family: a compact, Llama-style base model for text completion and small-model experimentation.
What's inside?
β’ 230M parameters
β’ 32 transformer layers
β’ 2,048-token context window
β’ Grouped Query Attention: 12 attention heads, 4 KV heads
β’ 49,152-token vocabulary
β’ SwiGLU activation, RoPE and tied embeddings
β’ BF16 weights and Hugging Face Transformers support
β’ Apache 2.0 license
Training
The model was trained on approximately 40.4B tokens from FineWeb-Edu, DCLM-Baseline and FineMath using a single A100 SXM.
Reported zero-shot results
β’ HellaSwag: 37.18% normalized accuracy
β’ PIQA: 65.78% accuracy
β’ ARC-Easy: 57.11% accuracy
β’ ARC-Challenge: 26.28% normalized accuracy
Want to experiment?
Code on REPO.
Model, weights and usage example:
SupraLabs/Supra2.5-Ultra-Preview-001
SupraLabs has released the first preview of its Supra2.5-Ultra family: a compact, Llama-style base model for text completion and small-model experimentation.
What's inside?
β’ 230M parameters
β’ 32 transformer layers
β’ 2,048-token context window
β’ Grouped Query Attention: 12 attention heads, 4 KV heads
β’ 49,152-token vocabulary
β’ SwiGLU activation, RoPE and tied embeddings
β’ BF16 weights and Hugging Face Transformers support
β’ Apache 2.0 license
Training
The model was trained on approximately 40.4B tokens from FineWeb-Edu, DCLM-Baseline and FineMath using a single A100 SXM.
Reported zero-shot results
β’ HellaSwag: 37.18% normalized accuracy
β’ PIQA: 65.78% accuracy
β’ ARC-Easy: 57.11% accuracy
β’ ARC-Challenge: 26.28% normalized accuracy
Want to experiment?
Code on REPO.
Model, weights and usage example:
SupraLabs/Supra2.5-Ultra-Preview-001
reacted to mithulaartigala's post with π₯ about 1 month ago
replied to DedeProGames's post about 1 month ago
Wishing you a strong fresh start with SupraLabs. The focused direction sounds promisingβlooking forward to seeing what you build next.
You are so cool bro ngl
replied to Banaxi-Tech's post about 1 month ago
@LH-Tech-AI @AxionLab-official which model are you talking about?
That BGA shitty thing
replied to Banaxi-Tech's post about 1 month ago
If you are going to make the same slop shit you already did, you should stop. Please stop using AI to make AI slop.
reacted to Banaxi-Tech's post with π about 1 month ago
Post
4,535
Hi everyone, we're back!
And we're releasing something major again now, if you have seen Grok Bot, its very powerful, but there isn't really a local alternative yet.
Today we're releasing Minds, they're personal AI bots that live on your computer.
They can run anywhere, on your phone, on your mac, on windows, and even on linux.
They support OpenAI Oauth as the main integration because most people already have a ChatGPT sub.
But locally, It supports ANY openai compatible api which allows you to setup ollama and llama.cpp and everything else.
It uses Jev for command approval on OpenRouter and Muse Spark Transcribe for transcription.
Its fully Open Source!
Check it out: https://github.com/BananaMind/Minds
And we're releasing something major again now, if you have seen Grok Bot, its very powerful, but there isn't really a local alternative yet.
Today we're releasing Minds, they're personal AI bots that live on your computer.
They can run anywhere, on your phone, on your mac, on windows, and even on linux.
They support OpenAI Oauth as the main integration because most people already have a ChatGPT sub.
But locally, It supports ANY openai compatible api which allows you to setup ollama and llama.cpp and everything else.
It uses Jev for command approval on OpenRouter and Muse Spark Transcribe for transcription.
Its fully Open Source!
Check it out: https://github.com/BananaMind/Minds
reacted to DedeProGames's post with π₯ππ€β€οΈ about 1 month ago
Post
5,150
Iβve just left
BananaMind to focus my work on
SupraLabs .
Following some internal pressure from SupraLabs and issues @Banaxi-Tech encountered with certain architectures, I decided it was time to change direction.
I want to thank
BananaMind for inviting me to join their organization and for helping shape my knowledge and passion regarding SLMs.
Now, itβs just me and
SupraLabs .
Following some internal pressure from SupraLabs and issues @Banaxi-Tech encountered with certain architectures, I decided it was time to change direction.
I want to thank
Now, itβs just me and
replied to Banaxi-Tech's post about 1 month ago
Bananamind3 is getting delayed lmao