This collection is provided for reproducibility of the paper's main claim
Andrey PRO
Bochkov
AI & ML interests
None yet
Recent Activity
published an article 3 days ago
FEM-ASM: Modular Language Computation updated a model 3 days ago
Bochkov/modular-reasoning-0p5b-g6p5-demo updated a model 3 days ago
Bochkov/fem-multi-mesh-1p7bOrganizations
This collection is provided for reproducibility of the paper's main claim
-
Bochkov/llm-fix-min-baseline-learned-input-table-model-classic
Text Generation • 0.5B • Updated • 332 -
Bochkov/llm-fix-min-fixed-minimal-binary-code
Text Generation • 0.5B • Updated • 338 -
Bochkov/llm-fix-min-affine-recoded-minimal-code-table-free
Text Generation • 0.5B • Updated • 323 -
Language Models Without a Trainable Input Embedding Table: Learning from Fixed Minimal Binary Token Codes
Paper • 2605.09751 • Published
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 • 169 -
Bochkov/growing-transformers-model-unicode-1-9-247m
Text Generation • 0.2B • Updated • 32 -
Bochkov/growing-transformers-model-unfrozen-1-9-247m
Text Generation • 0.2B • Updated • 153 -
Bochkov/growing-transformers-model-frozen-16-bit-baseline-monolyth-181m
Text Generation • 0.2B • Updated • 26
This collection is provided for reproducibility of the paper's main claim
-
Bochkov/ab_ext_learned
Text Generation • 2B • Updated • 605 -
Bochkov/ab_ext_binary16
Text Generation • 2B • Updated • 571 -
Bochkov/ab_ext_gf2
Text Generation • 2B • Updated • 537 -
Do Language Models Need a Trainable Input Embedding Table? Fixed Minimal Token Codes at 1.7B-Class Scale
Paper • 2610.04002 • Published • 4
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 • 24 -
Bochkov/emergent-semantics-model-unfrozen-335m
Text Generation • 0.3B • Updated • 21 -
Bochkov/emergent-semantics-model-16-bit-269m
Text Generation • 0.3B • Updated • 25 • 1 -
Bochkov/emergent-semantics-model-64-bit-272m
Text Generation • 0.3B • Updated • 135
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
-
Bochkov/ab_ext_learned
Text Generation • 2B • Updated • 605 -
Bochkov/ab_ext_binary16
Text Generation • 2B • Updated • 571 -
Bochkov/ab_ext_gf2
Text Generation • 2B • Updated • 537 -
Do Language Models Need a Trainable Input Embedding Table? Fixed Minimal Token Codes at 1.7B-Class Scale
Paper • 2610.04002 • Published • 4
This collection is provided for reproducibility of the paper's main claim
-
Bochkov/llm-fix-min-baseline-learned-input-table-model-classic
Text Generation • 0.5B • Updated • 332 -
Bochkov/llm-fix-min-fixed-minimal-binary-code
Text Generation • 0.5B • Updated • 338 -
Bochkov/llm-fix-min-affine-recoded-minimal-code-table-free
Text Generation • 0.5B • Updated • 323 -
Language Models Without a Trainable Input Embedding Table: Learning from Fixed Minimal Binary Token Codes
Paper • 2605.09751 • Published
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 • 24 -
Bochkov/emergent-semantics-model-unfrozen-335m
Text Generation • 0.3B • Updated • 21 -
Bochkov/emergent-semantics-model-16-bit-269m
Text Generation • 0.3B • Updated • 25 • 1 -
Bochkov/emergent-semantics-model-64-bit-272m
Text Generation • 0.3B • Updated • 135
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 • 169 -
Bochkov/growing-transformers-model-unicode-1-9-247m
Text Generation • 0.2B • Updated • 32 -
Bochkov/growing-transformers-model-unfrozen-1-9-247m
Text Generation • 0.2B • Updated • 153 -
Bochkov/growing-transformers-model-frozen-16-bit-baseline-monolyth-181m
Text Generation • 0.2B • Updated • 26
This collection features frozen, precomputed token embedding tensors designed for experimentation with semantic emergence in language models.