This collection is provided for reproducibility of the paper's main claim
🔄 In a Training Loop
Andrey
Bochkov
AI & ML interests
None yet
Recent Activity
updated a model 1 day ago
Bochkov/ab_ext_learned updated a model 1 day ago
Bochkov/modular-reasoning-0p5b-g6p5-demo updated a model 1 day ago
Bochkov/fem-multi-mesh-1p7bOrganizations
None yet
This collection is provided for reproducibility of the paper's main claim
Paper: 2507.07129 'Growing Transformers: Modular Composition and Layer-wise Expansion on a Frozen Substrate' (4.2.2, 5.2. Results)
-
Bochkov/growing-transformers-model-16-bit-1-9-181m
Text Generation • 0.2B • Updated • 149 -
Bochkov/growing-transformers-model-unicode-1-9-247m
Text Generation • 0.2B • Updated • 27 -
Bochkov/growing-transformers-model-unfrozen-1-9-247m
Text Generation • 0.2B • Updated • 140 -
Bochkov/growing-transformers-model-frozen-16-bit-baseline-monolyth-181m
Text Generation • 0.2B • Updated • 25
This collection is provided for reproducibility of the paper's main claim
Paper: 2507.04886 (TMLR, Oct 2025). 'Emergent Semantics Beyond Token Embeddings: Transformer LMs with Frozen Visual Unicode Representations'
-
Bochkov/emergent-semantics-model-uni-glyph-335m
Text Generation • 0.3B • Updated • 18 -
Bochkov/emergent-semantics-model-unfrozen-335m
Text Generation • 0.3B • Updated • 17 -
Bochkov/emergent-semantics-model-16-bit-269m
Text Generation • 0.3B • Updated • 18 • 1 -
Bochkov/emergent-semantics-model-64-bit-272m
Text Generation • 0.3B • Updated • 125
This collection features frozen, precomputed token embedding tensors designed for experimentation with semantic emergence in language models.
This collection is provided for reproducibility of the paper's main claim
This collection is provided for reproducibility of the paper's main claim
This collection is provided for reproducibility of the paper's main claim
Paper: 2507.04886 (TMLR, Oct 2025). 'Emergent Semantics Beyond Token Embeddings: Transformer LMs with Frozen Visual Unicode Representations'
-
Bochkov/emergent-semantics-model-uni-glyph-335m
Text Generation • 0.3B • Updated • 18 -
Bochkov/emergent-semantics-model-unfrozen-335m
Text Generation • 0.3B • Updated • 17 -
Bochkov/emergent-semantics-model-16-bit-269m
Text Generation • 0.3B • Updated • 18 • 1 -
Bochkov/emergent-semantics-model-64-bit-272m
Text Generation • 0.3B • Updated • 125
Paper: 2507.07129 'Growing Transformers: Modular Composition and Layer-wise Expansion on a Frozen Substrate' (4.2.2, 5.2. Results)
-
Bochkov/growing-transformers-model-16-bit-1-9-181m
Text Generation • 0.2B • Updated • 149 -
Bochkov/growing-transformers-model-unicode-1-9-247m
Text Generation • 0.2B • Updated • 27 -
Bochkov/growing-transformers-model-unfrozen-1-9-247m
Text Generation • 0.2B • Updated • 140 -
Bochkov/growing-transformers-model-frozen-16-bit-baseline-monolyth-181m
Text Generation • 0.2B • Updated • 25
This collection features frozen, precomputed token embedding tensors designed for experimentation with semantic emergence in language models.