Article
Andrey PRO
Bochkov
AI & ML interests
None yet
Recent Activity
updated a model 24 days ago
Bochkov/modular-reasoning-0p5b-g6p5-demo updated a model 24 days ago
Bochkov/fem-multi-mesh-1p7b published an article about 1 month ago
Modular Language Computation: From Multi-Mesh Models to External Memory and SkillsOrganizations
Articles 3
Article
Token Identity Is Not Meaning: What Fixed-Input Language Models Can Teach Us
Do Language Models Need a Trainable Input Embedding Table?
This collection is provided for reproducibility of the paper's main claim
-
Bochkov/ab_ext_learned
Text Generation • 2B • Updated • 80 -
Bochkov/ab_ext_binary16
Text Generation • 2B • Updated • 89 -
Bochkov/ab_ext_gf2
Text Generation • 2B • Updated • 99 -
Do Language Models Need a Trainable Input Embedding Table? Fixed Minimal Token Codes at 1.7B-Class Scale
Paper • 2610.04002 • Published • 5
Beyond the Parameter Monolith: Modular Language Modeling
This collection is provided for reproducibility of the paper's main claim
Do Language Models Need a Trainable Input Embedding Table?
This collection is provided for reproducibility of the paper's main claim
-
Bochkov/ab_ext_learned
Text Generation • 2B • Updated • 80 -
Bochkov/ab_ext_binary16
Text Generation • 2B • Updated • 89 -
Bochkov/ab_ext_gf2
Text Generation • 2B • Updated • 99 -
Do Language Models Need a Trainable Input Embedding Table? Fixed Minimal Token Codes at 1.7B-Class Scale
Paper • 2610.04002 • Published • 5
models 24
Bochkov/modular-reasoning-0p5b-g6p5-demo
Text Generation • 0.5B • Updated • 431
Bochkov/fem-multi-mesh-1p7b
Text Generation • 2B • Updated • 436
Bochkov/ab_ext_gf2
Text Generation • 2B • Updated • 99
Bochkov/ab_ext_binary16
Text Generation • 2B • Updated • 89
Bochkov/ab_ext_learned
Text Generation • 2B • Updated • 80
Bochkov/llm-fix-min-affine-recoded-minimal-code-table-free
Text Generation • 0.5B • Updated • 86
Bochkov/llm-fix-min-fixed-minimal-binary-code
Text Generation • 0.5B • Updated • 87
Bochkov/llm-fix-min-baseline-learned-input-table-model-classic
Text Generation • 0.5B • Updated • 59
Bochkov/growing-transformers-model-frozen-16-bit-baseline-monolyth-181m
Text Generation • 0.2B • Updated • 22
Bochkov/growing-transformers-model-unfrozen-baseline-monolyth-247m
Text Generation • 0.2B • Updated • 29