ensemble / tests

266 kB

Ctrl+K

1 contributor

History: 6 commits

thefinalboss

v0.5.1: morphological filtering in solve_analogy (50%->62%), cosmul option exposed, cosadd default

593be8a verified 2 days ago

__pycache__
v0.5.1: morphological filtering in solve_analogy (50%->62%), cosmul option exposed, cosadd default 2 days ago
__init__.py

0 Bytes
Initial release: ENSEMBLE training-free AI — compressed .exp experts + Kuramoto brain 4 days ago
test_attractor.py

3.09 kB
Initial release: ENSEMBLE training-free AI — compressed .exp experts + Kuramoto brain 4 days ago
test_bench.py

2.7 kB
Initial release: ENSEMBLE training-free AI — compressed .exp experts + Kuramoto brain 4 days ago
test_bpe_expert.py

5.38 kB
v0.2: global shared BPE tokenizer + persistent central brain memory + brain save/load. BPE lifts quality ceiling (TinyStories 150KB D=5000: next-token acc 94.5% -> 98.5%, latency 112ms -> 28ms, RAM halved). BrainMemory grows via thinking and survives save/load. 75 tests. 4 days ago
test_brain.py

3.43 kB
Initial release: ENSEMBLE training-free AI — compressed .exp experts + Kuramoto brain 4 days ago
test_brain_memory.py

4.16 kB
v0.2: global shared BPE tokenizer + persistent central brain memory + brain save/load. BPE lifts quality ceiling (TinyStories 150KB D=5000: next-token acc 94.5% -> 98.5%, latency 112ms -> 28ms, RAM halved). BrainMemory grows via thinking and survives save/load. 75 tests. 4 days ago
test_embedding.py

7.14 kB
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. 3 days ago
test_expert.py

6.78 kB
v0.2: global shared BPE tokenizer + persistent central brain memory + brain save/load. BPE lifts quality ceiling (TinyStories 150KB D=5000: next-token acc 94.5% -> 98.5%, latency 112ms -> 28ms, RAM halved). BrainMemory grows via thinking and survives save/load. 75 tests. 4 days ago
test_integration.py

3.36 kB
v0.2: global shared BPE tokenizer + persistent central brain memory + brain save/load. BPE lifts quality ceiling (TinyStories 150KB D=5000: next-token acc 94.5% -> 98.5%, latency 112ms -> 28ms, RAM halved). BrainMemory grows via thinking and survives save/load. 75 tests. 4 days ago
test_structural.py

5.73 kB
v0.3: structural query encoding (patterns + slots) for generalization. Expert.from_qa_pairs now accepts patterns=[...]; questions matching a template are encoded as bind(pattern_hv, slot_hv). On a capitals holdout benchmark, char-level returns empty 100% of the time on unseen slots; structural returns a well-formed answer 100% of the time (+100 pts graceful degradation). Honest: format-generalized guesses by analogy, not factual correctness (no embeddings). 91 tests passing. 3 days ago