Transformers grown layer-by-layer on frozen embeddings. Explores emergent capabilities with depth.
Andrey
Bochkov
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 22 hours ago
Emergent Semantics Beyond Token Embeddings: Transformer LMs with Frozen
Visual Unicode Representations
upvoted
a
paper
about 22 hours ago
Growing Transformers: Modular Composition and Layer-wise Expansion on a
Frozen Substrate
commented on
a paper
about 22 hours ago
Emergent Semantics Beyond Token Embeddings: Transformer LMs with Frozen
Visual Unicode Representations
Organizations
None yet
models
25
Bochkov/bvv241-abs
Updated
•
11
Bochkov/bvv241-nemo
Updated
•
8
Bochkov/bvv241-max
Updated
•
12
Bochkov/bvv241-2-3
Updated
•
11
Bochkov/pro_bvv_en
Text Generation
•
Updated
•
27
Bochkov/pro_bvv_unfrozen
Text Generation
•
Updated
•
22
Bochkov/pro_bvv_ru
Text Generation
•
Updated
•
13
Bochkov/pro_bvv_zh
Text Generation
•
Updated
•
11
Bochkov/nemo_bvv_zh
Updated
•
13
Bochkov/nemo_bvv_ru
Updated
•
17
datasets
0
None public yet