🏗️ Building on HF

Dan P

Datdanboi25

90 5 142

https://huggingface.co/AxiomicLabs

AI & ML interests

Axiomic Labs Founder Mechatronics engineer, LLMs, Vision Models, Embedding Models

Recent Activity

liked a model about 18 hours ago

AxionLab-official/RizzAura-100k

liked a model about 20 hours ago

Nikity/lille-130m-base

liked a Space 1 day ago

finnianx/Gros-Michel-Translator

View all activity

Organizations

liked a model about 18 hours ago

AxionLab-official/RizzAura-100k

Text Generation • Updated about 18 hours ago • 193 • 3

liked a model about 20 hours ago

Nikity/lille-130m-base

Text Generation • 0.1B • Updated Sep 4, 2025 • 87 • 16

liked a Space 1 day ago

Gros Michel Translator

🦀

A space to try out the Gros Michel Translation model.

liked a model 2 days ago

syntropic-clx/Clyx_0.2-115.67M-BASE

Text Generation • 0.1B • Updated Jun 7 • 42 • 3

New activity in AxiomicLabs/Open_SLM_Leaderboard 2 days ago

Add Nexus-Erebus-50M (Ideoa Labs, from-scratch 54M)

#39 opened 3 days ago by

MaliosDark

liked a model 3 days ago

MaliosDark/Nexus-Erebus-50M

Text Generation • 54.1M • Updated 3 days ago • 607 • 4

New activity in AxiomicLabs/Open_SLM_Leaderboard 4 days ago

Add https://huggingface.co/BananaMind/BananaMind-2-Mini

#37 opened 4 days ago by

Banaxi-Tech

Hierarchos experiment

#38 opened 4 days ago by

netcat420

liked 3 models 4 days ago

updated a Space 4 days ago

Open SLM Leaderboard

🏆

Open Small Language Model Leaderboard

reacted to ucr-max's post with 🔥 4 days ago

Post

Published under Universal Computing Research: Atom2.7m, a 2.74M-parameter causal LM experiment with arithmetic-aware numeric representation.

It keeps regular BPE-style text continuation, while adding structure for numeric spans: digit ordering, place_ids, and role_ids.

Atom2.7m reaches 69.24% accuracy on ArithMark2.0.

The question behind the project is narrow: how much of small-model arithmetic performance depends on representation, rather than scale alone?

Model: UniversalComputingResearch/Atom2.7m
Article: https://huggingface.co/blog/ucr-max/atom2-7m-arithmetic-representation
Demo: UniversalComputingResearch/Atom2.7-Demo

1 reply

New activity in AxiomicLabs/Open_SLM_Leaderboard 4 days ago

Add Banaxi-Tech/waterfall-alpha

#36 opened 5 days ago by

Banaxi-Tech

upvoted an article 5 days ago

Article

Atom2.7m: Representation-Level Specialization for Arithmetic-Aware Small Language Models

ucr-max

•

5 days ago

• 7

liked a Space 5 days ago

Arithmetic-SLM

🧮

Tiny 31.7M SLM that solves arithmetic expressions

reacted to PhysiQuanty's post with 🔥 5 days ago

Post

4586

🧠 Arithmetic-SLM : A 30M model that manages to compute simple arithmetic better than a 3B model 🚀
WhirlwindAI/Arithmetic-SLM
WhirlwindAI/arithmetic-slm

🏆 Leaderboard ArithMark-2 🏆
🥇 Qwen/Qwen2.5-Math-1.5B = 82.08%
🥈 WhirlwindAI/Arithmetic-SLM = 78.60% (31.7M Params)
🥉 Qwen/Qwen2.5-3B = 78.44%

Example WhirlwindAI/Arithmetic-SLM =
0.5 * 0.5 = 0.25 ✅
105 + 45 / 8 = 110 ✅
(132 / 12) + (46 - 15) = 42 ✅
(10 + 28) * 3 = 114 ✅
1 * (16 + 28) = 44 ✅
(21 + 27) * (14 - 7) = 336 ❌

leaderboard = """
|              Model               |    Params    |   Score   |
|----------------------------------|--------------|-----------|
|      Qwen/Qwen2.5-Math-1.5B      |     1.54B    |   82.08%  |
|    WhirlwindAI/Arithmetic-SLM    |    31.70M    |   78.60%  | <=
|         Qwen/Qwen2.5-3B          |     3.09B    |   78.44%  |
|        Qwen/Qwen2.5-1.5B         |     1.54B    |   77.72%  |
|    Qwen/Qwen2.5-Coder-1.5B       |     1.54B    |   74.88%  |
|   HuggingFaceTB/SmolLM2-1.7B     |     1.71B    |   66.12%  |
|        Qwen/Qwen2.5-0.5B         |      494M    |   63.04%  |
| facebook/MobileLLM-R1-140M-base  |      140M    |   53.88%  |
|     SupraLabs/Supra-50M-Base     |       52M    |   27.12%  |
"""