Compact Language Model Index
📊
5
Chance-normalized evaluation of compact language models.
AI & ML interests
None defined yet.
Recent Activity
View all activity
ucr-max
updated a
Space 21 minutes ago
Post
1859
We have released the first version of CompactLMIndex UniversalComputingResearch/clmi, a curated benchmark for smaller language models.
The index evaluates models across six benchmarks covering commonsense, science and world knowledge, and grammatical competence. Scores are normalized for random chance, so results are easier to compare across tasks with different baselines.
The composite gives 50% weight to commonsense, 25% to science and world knowledge, and 25% to grammatical competence. BLiMP is macro-averaged across its 12 linguistic categories. Every result includes 95% bootstrap intervals, and rank ranges reflect paired comparisons on matched evaluation items.
The goal is to compare compact models under one fixed, zero-shot evaluation protocol and make differences in architecture, training, and inference visible without treating parameter count as a substitute for quality.
If you have results for a model that fits the benchmark scope, please open a discussion on the Space.
The index evaluates models across six benchmarks covering commonsense, science and world knowledge, and grammatical competence. Scores are normalized for random chance, so results are easier to compare across tasks with different baselines.
The composite gives 50% weight to commonsense, 25% to science and world knowledge, and 25% to grammatical competence. BLiMP is macro-averaged across its 12 linguistic categories. Every result includes 95% bootstrap intervals, and rank ranges reflect paired comparisons on matched evaluation items.
The goal is to compare compact models under one fixed, zero-shot evaluation protocol and make differences in architecture, training, and inference visible without treating parameter count as a substitute for quality.
If you have results for a model that fits the benchmark scope, please open a discussion on the Space.
ucr-max
published a
Space about 20 hours ago
Kudos on Atom 2.7M
🤗 1
4
#1 opened 13 days ago
by 
Mmorgan-ML
ucr-max
updated a
Space 13 days ago
Post
135
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
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
ucr-max
updated a
Space 14 days ago
ucr-max
published a
Space 14 days ago
ucr-max
updated a
model 15 days ago
ucr-max
updated a
dataset 20 days ago
ucr-max
published a
dataset 20 days ago
ucr-max
published a
Space 20 days ago
ucr-max
published a
model 21 days ago
ucr-max
updated a
model about 1 month ago
ucr-max
published a
model about 1 month ago