Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
thefinalboss
/
ensemble
like
0
English
ensemble
hyperdimensional-computing
vector-symbolic-architectures
associative-memory
training-free
kuramoto
ensemble-methods
cpu
no-gpu
memory-augmented
bpe
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
ensemble
1.21 MB
Ctrl+K
Ctrl+K
1 contributor
History:
7 commits
thefinalboss
v0.5.1: morphological filtering in solve_analogy (50%->62%), cosmul option exposed, cosadd default
593be8a
verified
about 19 hours ago
.pytest_cache
v0.5: factual generalization via dense analogy. learn_relation + solve_analogy implement Mikolov paris-france+spain=madrid in normalized dense space, averaged over known examples, excluding the query slot. Wired into structural answer() so unseen slots get plain-text answers. Measured end-to-end via the Brain with fastText: capitals holdout goes 0% (char) / 0% (structural) -> ~50-67% factual-correct (spain->madrid, portugal->lisbon, greece->athens, norway->oslo recovered correctly). from_fasttext uses batch projection (fast load). The semantic wall is broken. 109 tests.
1 day ago
bench
v0.5.1: morphological filtering in solve_analogy (50%->62%), cosmul option exposed, cosadd default
about 19 hours ago
ensemble
v0.5.1: morphological filtering in solve_analogy (50%->62%), cosmul option exposed, cosadd default
about 19 hours ago
palimseste
v0.5.1: morphological filtering in solve_analogy (50%->62%), cosmul option exposed, cosadd default
about 19 hours ago
tests
v0.5.1: morphological filtering in solve_analogy (50%->62%), cosmul option exposed, cosadd default
about 19 hours ago
.gitattributes
Safe
1.52 kB
initial commit
3 days ago
LICENSE
1.07 kB
Initial release: ENSEMBLE training-free AI โ compressed .exp experts + Kuramoto brain
3 days ago
README.md
15.1 kB
v0.5.1: morphological filtering in solve_analogy (50%->62%), cosmul option exposed, cosadd default
about 19 hours ago
RESULTS.md
5.45 kB
Initial release: ENSEMBLE training-free AI โ compressed .exp experts + Kuramoto brain
3 days ago
pyproject.toml
908 Bytes
Initial release: ENSEMBLE training-free AI โ compressed .exp experts + Kuramoto brain
3 days ago